mingle/streamingle-unity-utilities
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

release(camera-ai): publish 0.4.12 catalog portability fix

Browse Source
This commit is contained in:
KINDNICK
2026-08-16 01:05:07 +09:00
parent 8e5e2e8ad0
commit b65e54a7e8
211 changed files with 45990 additions and 45913 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/_svmlight_format_fast.pyx
+252 -252
View File
@@ -1,252 +1,252 @@
# Optimized inner loop of load_svmlight_file.
#
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import array
from cpython cimport array
cimport cython
from libc.string cimport strchr
import numpy as np
cdef bytes COMMA = u','.encode('ascii')
cdef bytes COLON = u':'.encode('ascii')
def _load_svmlight_file(f, dtype, bint multilabel, bint zero_based,
bint query_id, long long offset, long long length):
cdef array.array data, indices, indptr
cdef bytes line
cdef char *hash_ptr
cdef char *line_cstr
cdef int idx, prev_idx
cdef Py_ssize_t i
cdef bytes qid_prefix = b'qid'
cdef Py_ssize_t n_features
cdef long long offset_max = offset + length if length > 0 else -1
# Special-case float32 but use float64 for everything else;
# the Python code will do further conversions.
if dtype == np.float32:
data = array.array("f")
else:
dtype = np.float64
data = array.array("d")
indices = array.array("q")
indptr = array.array("q", [0])
query = np.arange(0, dtype=np.int64)
if multilabel:
labels = []
else:
labels = array.array("d")
if offset > 0:
f.seek(offset)
# drop the current line that might be truncated and is to be
# fetched by another call
f.readline()
for line in f:
# skip comments
line_cstr = line
hash_ptr = strchr(line_cstr, 35) # ASCII value of '#' is 35
if hash_ptr != NULL:
line = line[:hash_ptr - line_cstr]
line_parts = line.split()
if len(line_parts) == 0:
continue
target, features = line_parts[0], line_parts[1:]
if multilabel:
if COLON in target:
target, features = [], line_parts[0:]
else:
target = [float(y) for y in target.split(COMMA)]
target.sort()
labels.append(tuple(target))
else:
array.resize_smart(labels, len(labels) + 1)
labels[len(labels) - 1] = float(target)
prev_idx = -1
n_features = len(features)
if n_features and features[0].startswith(qid_prefix):
_, value = features[0].split(COLON, 1)
if query_id:
query.resize(len(query) + 1)
query[len(query) - 1] = np.int64(value)
features.pop(0)
n_features -= 1
for i in range(0, n_features):
idx_s, value = features[i].split(COLON, 1)
idx = int(idx_s)
if idx < 0 or not zero_based and idx == 0:
raise ValueError(
"Invalid index %d in SVMlight/LibSVM data file." % idx)
if idx <= prev_idx:
raise ValueError("Feature indices in SVMlight/LibSVM data "
"file should be sorted and unique.")
array.resize_smart(indices, len(indices) + 1)
indices[len(indices) - 1] = idx
array.resize_smart(data, len(data) + 1)
data[len(data) - 1] = float(value)
prev_idx = idx
# increment index pointer array size
array.resize_smart(indptr, len(indptr) + 1)
indptr[len(indptr) - 1] = len(data)
if offset_max != -1 and f.tell() > offset_max:
# Stop here and let another call deal with the following.
break
return (dtype, data, indices, indptr, labels, query)
# Two fused types are defined to be able to
# use all possible combinations of parameters.
ctypedef fused int_or_float:
cython.integral
cython.floating
signed long long
ctypedef fused double_or_longlong:
double
signed long long
ctypedef fused int_or_longlong:
cython.integral
signed long long
def get_dense_row_string(
const int_or_float[:, :] X,
Py_ssize_t[:] x_inds,
double_or_longlong[:] x_vals,
Py_ssize_t row,
str value_pattern,
bint one_based,
):
cdef:
Py_ssize_t row_length = X.shape[1]
Py_ssize_t x_nz_used = 0
Py_ssize_t k
int_or_float val
for k in range(row_length):
val = X[row, k]
if val == 0:
continue
x_inds[x_nz_used] = k
x_vals[x_nz_used] = <double_or_longlong> val
x_nz_used += 1
reprs = [
value_pattern % (x_inds[i] + one_based, x_vals[i])
for i in range(x_nz_used)
]
return " ".join(reprs)
def get_sparse_row_string(
int_or_float[:] X_data,
int[:] X_indptr,
int[:] X_indices,
Py_ssize_t row,
str value_pattern,
bint one_based,
):
cdef:
Py_ssize_t row_start = X_indptr[row]
Py_ssize_t row_end = X_indptr[row+1]
reprs = [
value_pattern % (X_indices[i] + one_based, X_data[i])
for i in range(row_start, row_end)
]
return " ".join(reprs)
def _dump_svmlight_file(
X,
y,
f,
bint multilabel,
bint one_based,
int_or_longlong[:] query_id,
bint X_is_sp,
bint y_is_sp,
):
cdef bint X_is_integral
cdef bint query_id_is_not_empty = query_id.size > 0
X_is_integral = X.dtype.kind == "i"
if X_is_integral:
value_pattern = "%d:%d"
else:
value_pattern = "%d:%.16g"
if y.dtype.kind == "i":
label_pattern = "%d"
else:
label_pattern = "%.16g"
line_pattern = "%s"
if query_id_is_not_empty:
line_pattern += " qid:%d"
line_pattern += " %s\n"
cdef:
Py_ssize_t num_labels = y.shape[1]
Py_ssize_t x_len = X.shape[0]
Py_ssize_t row_length = X.shape[1]
Py_ssize_t i
Py_ssize_t j
Py_ssize_t col_start
Py_ssize_t col_end
Py_ssize_t[:] x_inds = np.empty(row_length, dtype=np.intp)
signed long long[:] x_vals_int
double[:] x_vals_float
if not X_is_sp:
if X_is_integral:
x_vals_int = np.zeros(row_length, dtype=np.longlong)
else:
x_vals_float = np.zeros(row_length, dtype=np.float64)
for i in range(x_len):
if not X_is_sp:
if X_is_integral:
s = get_dense_row_string(X, x_inds, x_vals_int, i, value_pattern, one_based)
else:
s = get_dense_row_string(X, x_inds, x_vals_float, i, value_pattern, one_based)
else:
s = get_sparse_row_string(X.data, X.indptr, X.indices, i, value_pattern, one_based)
if multilabel:
if y_is_sp:
col_start = y.indptr[i]
col_end = y.indptr[i+1]
labels_str = ','.join(tuple(label_pattern % y.indices[j] for j in range(col_start, col_end) if y.data[j] != 0))
else:
labels_str = ','.join(label_pattern % j for j in range(num_labels) if y[i, j] != 0)
else:
if y_is_sp:
labels_str = label_pattern % y.data[i]
else:
labels_str = label_pattern % y[i, 0]
if query_id_is_not_empty:
feat = (labels_str, query_id[i], s)
else:
feat = (labels_str, s)
f.write((line_pattern % feat).encode("utf-8"))
# Optimized inner loop of load_svmlight_file.
#
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import array
from cpython cimport array
cimport cython
from libc.string cimport strchr
import numpy as np
cdef bytes COMMA = u','.encode('ascii')
cdef bytes COLON = u':'.encode('ascii')
def _load_svmlight_file(f, dtype, bint multilabel, bint zero_based,
bint query_id, long long offset, long long length):
cdef array.array data, indices, indptr
cdef bytes line
cdef char *hash_ptr
cdef char *line_cstr
cdef int idx, prev_idx
cdef Py_ssize_t i
cdef bytes qid_prefix = b'qid'
cdef Py_ssize_t n_features
cdef long long offset_max = offset + length if length > 0 else -1
# Special-case float32 but use float64 for everything else;
# the Python code will do further conversions.
if dtype == np.float32:
data = array.array("f")
else:
dtype = np.float64
data = array.array("d")
indices = array.array("q")
indptr = array.array("q", [0])
query = np.arange(0, dtype=np.int64)
if multilabel:
labels = []
else:
labels = array.array("d")
if offset > 0:
f.seek(offset)
# drop the current line that might be truncated and is to be
# fetched by another call
f.readline()
for line in f:
# skip comments
line_cstr = line
hash_ptr = strchr(line_cstr, 35) # ASCII value of '#' is 35
if hash_ptr != NULL:
line = line[:hash_ptr - line_cstr]
line_parts = line.split()
if len(line_parts) == 0:
continue
target, features = line_parts[0], line_parts[1:]
if multilabel:
if COLON in target:
target, features = [], line_parts[0:]
else:
target = [float(y) for y in target.split(COMMA)]
target.sort()
labels.append(tuple(target))
else:
array.resize_smart(labels, len(labels) + 1)
labels[len(labels) - 1] = float(target)
prev_idx = -1
n_features = len(features)
if n_features and features[0].startswith(qid_prefix):
_, value = features[0].split(COLON, 1)
if query_id:
query.resize(len(query) + 1)
query[len(query) - 1] = np.int64(value)
features.pop(0)
n_features -= 1
for i in range(0, n_features):
idx_s, value = features[i].split(COLON, 1)
idx = int(idx_s)
if idx < 0 or not zero_based and idx == 0:
raise ValueError(
"Invalid index %d in SVMlight/LibSVM data file." % idx)
if idx <= prev_idx:
raise ValueError("Feature indices in SVMlight/LibSVM data "
"file should be sorted and unique.")
array.resize_smart(indices, len(indices) + 1)
indices[len(indices) - 1] = idx
array.resize_smart(data, len(data) + 1)
data[len(data) - 1] = float(value)
prev_idx = idx
# increment index pointer array size
array.resize_smart(indptr, len(indptr) + 1)
indptr[len(indptr) - 1] = len(data)
if offset_max != -1 and f.tell() > offset_max:
# Stop here and let another call deal with the following.
break
return (dtype, data, indices, indptr, labels, query)
# Two fused types are defined to be able to
# use all possible combinations of parameters.
ctypedef fused int_or_float:
cython.integral
cython.floating
signed long long
ctypedef fused double_or_longlong:
double
signed long long
ctypedef fused int_or_longlong:
cython.integral
signed long long
def get_dense_row_string(
const int_or_float[:, :] X,
Py_ssize_t[:] x_inds,
double_or_longlong[:] x_vals,
Py_ssize_t row,
str value_pattern,
bint one_based,
):
cdef:
Py_ssize_t row_length = X.shape[1]
Py_ssize_t x_nz_used = 0
Py_ssize_t k
int_or_float val
for k in range(row_length):
val = X[row, k]
if val == 0:
continue
x_inds[x_nz_used] = k
x_vals[x_nz_used] = <double_or_longlong> val
x_nz_used += 1
reprs = [
value_pattern % (x_inds[i] + one_based, x_vals[i])
for i in range(x_nz_used)
]
return " ".join(reprs)
def get_sparse_row_string(
int_or_float[:] X_data,
int[:] X_indptr,
int[:] X_indices,
Py_ssize_t row,
str value_pattern,
bint one_based,
):
cdef:
Py_ssize_t row_start = X_indptr[row]
Py_ssize_t row_end = X_indptr[row+1]
reprs = [
value_pattern % (X_indices[i] + one_based, X_data[i])
for i in range(row_start, row_end)
]
return " ".join(reprs)
def _dump_svmlight_file(
X,
y,
f,
bint multilabel,
bint one_based,
int_or_longlong[:] query_id,
bint X_is_sp,
bint y_is_sp,
):
cdef bint X_is_integral
cdef bint query_id_is_not_empty = query_id.size > 0
X_is_integral = X.dtype.kind == "i"
if X_is_integral:
value_pattern = "%d:%d"
else:
value_pattern = "%d:%.16g"
if y.dtype.kind == "i":
label_pattern = "%d"
else:
label_pattern = "%.16g"
line_pattern = "%s"
if query_id_is_not_empty:
line_pattern += " qid:%d"
line_pattern += " %s\n"
cdef:
Py_ssize_t num_labels = y.shape[1]
Py_ssize_t x_len = X.shape[0]
Py_ssize_t row_length = X.shape[1]
Py_ssize_t i
Py_ssize_t j
Py_ssize_t col_start
Py_ssize_t col_end
Py_ssize_t[:] x_inds = np.empty(row_length, dtype=np.intp)
signed long long[:] x_vals_int
double[:] x_vals_float
if not X_is_sp:
if X_is_integral:
x_vals_int = np.zeros(row_length, dtype=np.longlong)
else:
x_vals_float = np.zeros(row_length, dtype=np.float64)
for i in range(x_len):
if not X_is_sp:
if X_is_integral:
s = get_dense_row_string(X, x_inds, x_vals_int, i, value_pattern, one_based)
else:
s = get_dense_row_string(X, x_inds, x_vals_float, i, value_pattern, one_based)
else:
s = get_sparse_row_string(X.data, X.indptr, X.indices, i, value_pattern, one_based)
if multilabel:
if y_is_sp:
col_start = y.indptr[i]
col_end = y.indptr[i+1]
labels_str = ','.join(tuple(label_pattern % y.indices[j] for j in range(col_start, col_end) if y.data[j] != 0))
else:
labels_str = ','.join(label_pattern % j for j in range(num_labels) if y[i, j] != 0)
else:
if y_is_sp:
labels_str = label_pattern % y.data[i]
else:
labels_str = label_pattern % y[i, 0]
if query_id_is_not_empty:
feat = (labels_str, query_id[i], s)
else:
feat = (labels_str, s)
f.write((line_pattern % feat).encode("utf-8"))
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/data/breast_cancer.csv
+570 -570
View File
File diff suppressed because it is too large Load Diff
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/data/iris.csv
+151 -151
View File
@@ -1,151 +1,151 @@
150,4,setosa,versicolor,virginica
5.1,3.5,1.4,0.2,0
4.9,3.0,1.4,0.2,0
4.7,3.2,1.3,0.2,0
4.6,3.1,1.5,0.2,0
5.0,3.6,1.4,0.2,0
5.4,3.9,1.7,0.4,0
4.6,3.4,1.4,0.3,0
5.0,3.4,1.5,0.2,0
4.4,2.9,1.4,0.2,0
4.9,3.1,1.5,0.1,0
5.4,3.7,1.5,0.2,0
4.8,3.4,1.6,0.2,0
4.8,3.0,1.4,0.1,0
4.3,3.0,1.1,0.1,0
5.8,4.0,1.2,0.2,0
5.7,4.4,1.5,0.4,0
5.4,3.9,1.3,0.4,0
5.1,3.5,1.4,0.3,0
5.7,3.8,1.7,0.3,0
5.1,3.8,1.5,0.3,0
5.4,3.4,1.7,0.2,0
5.1,3.7,1.5,0.4,0
4.6,3.6,1.0,0.2,0
5.1,3.3,1.7,0.5,0
4.8,3.4,1.9,0.2,0
5.0,3.0,1.6,0.2,0
5.0,3.4,1.6,0.4,0
5.2,3.5,1.5,0.2,0
5.2,3.4,1.4,0.2,0
4.7,3.2,1.6,0.2,0
4.8,3.1,1.6,0.2,0
5.4,3.4,1.5,0.4,0
5.2,4.1,1.5,0.1,0
5.5,4.2,1.4,0.2,0
4.9,3.1,1.5,0.2,0
5.0,3.2,1.2,0.2,0
5.5,3.5,1.3,0.2,0
4.9,3.6,1.4,0.1,0
4.4,3.0,1.3,0.2,0
5.1,3.4,1.5,0.2,0
5.0,3.5,1.3,0.3,0
4.5,2.3,1.3,0.3,0
4.4,3.2,1.3,0.2,0
5.0,3.5,1.6,0.6,0
5.1,3.8,1.9,0.4,0
4.8,3.0,1.4,0.3,0
5.1,3.8,1.6,0.2,0
4.6,3.2,1.4,0.2,0
5.3,3.7,1.5,0.2,0
5.0,3.3,1.4,0.2,0
7.0,3.2,4.7,1.4,1
6.4,3.2,4.5,1.5,1
6.9,3.1,4.9,1.5,1
5.5,2.3,4.0,1.3,1
6.5,2.8,4.6,1.5,1
5.7,2.8,4.5,1.3,1
6.3,3.3,4.7,1.6,1
4.9,2.4,3.3,1.0,1
6.6,2.9,4.6,1.3,1
5.2,2.7,3.9,1.4,1
5.0,2.0,3.5,1.0,1
5.9,3.0,4.2,1.5,1
6.0,2.2,4.0,1.0,1
6.1,2.9,4.7,1.4,1
5.6,2.9,3.6,1.3,1
6.7,3.1,4.4,1.4,1
5.6,3.0,4.5,1.5,1
5.8,2.7,4.1,1.0,1
6.2,2.2,4.5,1.5,1
5.6,2.5,3.9,1.1,1
5.9,3.2,4.8,1.8,1
6.1,2.8,4.0,1.3,1
6.3,2.5,4.9,1.5,1
6.1,2.8,4.7,1.2,1
6.4,2.9,4.3,1.3,1
6.6,3.0,4.4,1.4,1
6.8,2.8,4.8,1.4,1
6.7,3.0,5.0,1.7,1
6.0,2.9,4.5,1.5,1
5.7,2.6,3.5,1.0,1
5.5,2.4,3.8,1.1,1
5.5,2.4,3.7,1.0,1
5.8,2.7,3.9,1.2,1
6.0,2.7,5.1,1.6,1
5.4,3.0,4.5,1.5,1
6.0,3.4,4.5,1.6,1
6.7,3.1,4.7,1.5,1
6.3,2.3,4.4,1.3,1
5.6,3.0,4.1,1.3,1
5.5,2.5,4.0,1.3,1
5.5,2.6,4.4,1.2,1
6.1,3.0,4.6,1.4,1
5.8,2.6,4.0,1.2,1
5.0,2.3,3.3,1.0,1
5.6,2.7,4.2,1.3,1
5.7,3.0,4.2,1.2,1
5.7,2.9,4.2,1.3,1
6.2,2.9,4.3,1.3,1
5.1,2.5,3.0,1.1,1
5.7,2.8,4.1,1.3,1
6.3,3.3,6.0,2.5,2
5.8,2.7,5.1,1.9,2
7.1,3.0,5.9,2.1,2
6.3,2.9,5.6,1.8,2
6.5,3.0,5.8,2.2,2
7.6,3.0,6.6,2.1,2
4.9,2.5,4.5,1.7,2
7.3,2.9,6.3,1.8,2
6.7,2.5,5.8,1.8,2
7.2,3.6,6.1,2.5,2
6.5,3.2,5.1,2.0,2
6.4,2.7,5.3,1.9,2
6.8,3.0,5.5,2.1,2
5.7,2.5,5.0,2.0,2
5.8,2.8,5.1,2.4,2
6.4,3.2,5.3,2.3,2
6.5,3.0,5.5,1.8,2
7.7,3.8,6.7,2.2,2
7.7,2.6,6.9,2.3,2
6.0,2.2,5.0,1.5,2
6.9,3.2,5.7,2.3,2
5.6,2.8,4.9,2.0,2
7.7,2.8,6.7,2.0,2
6.3,2.7,4.9,1.8,2
6.7,3.3,5.7,2.1,2
7.2,3.2,6.0,1.8,2
6.2,2.8,4.8,1.8,2
6.1,3.0,4.9,1.8,2
6.4,2.8,5.6,2.1,2
7.2,3.0,5.8,1.6,2
7.4,2.8,6.1,1.9,2
7.9,3.8,6.4,2.0,2
6.4,2.8,5.6,2.2,2
6.3,2.8,5.1,1.5,2
6.1,2.6,5.6,1.4,2
7.7,3.0,6.1,2.3,2
6.3,3.4,5.6,2.4,2
6.4,3.1,5.5,1.8,2
6.0,3.0,4.8,1.8,2
6.9,3.1,5.4,2.1,2
6.7,3.1,5.6,2.4,2
6.9,3.1,5.1,2.3,2
5.8,2.7,5.1,1.9,2
6.8,3.2,5.9,2.3,2
6.7,3.3,5.7,2.5,2
6.7,3.0,5.2,2.3,2
6.3,2.5,5.0,1.9,2
6.5,3.0,5.2,2.0,2
6.2,3.4,5.4,2.3,2
5.9,3.0,5.1,1.8,2
150,4,setosa,versicolor,virginica
5.1,3.5,1.4,0.2,0
4.9,3.0,1.4,0.2,0
4.7,3.2,1.3,0.2,0
4.6,3.1,1.5,0.2,0
5.0,3.6,1.4,0.2,0
5.4,3.9,1.7,0.4,0
4.6,3.4,1.4,0.3,0
5.0,3.4,1.5,0.2,0
4.4,2.9,1.4,0.2,0
4.9,3.1,1.5,0.1,0
5.4,3.7,1.5,0.2,0
4.8,3.4,1.6,0.2,0
4.8,3.0,1.4,0.1,0
4.3,3.0,1.1,0.1,0
5.8,4.0,1.2,0.2,0
5.7,4.4,1.5,0.4,0
5.4,3.9,1.3,0.4,0
5.1,3.5,1.4,0.3,0
5.7,3.8,1.7,0.3,0
5.1,3.8,1.5,0.3,0
5.4,3.4,1.7,0.2,0
5.1,3.7,1.5,0.4,0
4.6,3.6,1.0,0.2,0
5.1,3.3,1.7,0.5,0
4.8,3.4,1.9,0.2,0
5.0,3.0,1.6,0.2,0
5.0,3.4,1.6,0.4,0
5.2,3.5,1.5,0.2,0
5.2,3.4,1.4,0.2,0
4.7,3.2,1.6,0.2,0
4.8,3.1,1.6,0.2,0
5.4,3.4,1.5,0.4,0
5.2,4.1,1.5,0.1,0
5.5,4.2,1.4,0.2,0
4.9,3.1,1.5,0.2,0
5.0,3.2,1.2,0.2,0
5.5,3.5,1.3,0.2,0
4.9,3.6,1.4,0.1,0
4.4,3.0,1.3,0.2,0
5.1,3.4,1.5,0.2,0
5.0,3.5,1.3,0.3,0
4.5,2.3,1.3,0.3,0
4.4,3.2,1.3,0.2,0
5.0,3.5,1.6,0.6,0
5.1,3.8,1.9,0.4,0
4.8,3.0,1.4,0.3,0
5.1,3.8,1.6,0.2,0
4.6,3.2,1.4,0.2,0
5.3,3.7,1.5,0.2,0
5.0,3.3,1.4,0.2,0
7.0,3.2,4.7,1.4,1
6.4,3.2,4.5,1.5,1
6.9,3.1,4.9,1.5,1
5.5,2.3,4.0,1.3,1
6.5,2.8,4.6,1.5,1
5.7,2.8,4.5,1.3,1
6.3,3.3,4.7,1.6,1
4.9,2.4,3.3,1.0,1
6.6,2.9,4.6,1.3,1
5.2,2.7,3.9,1.4,1
5.0,2.0,3.5,1.0,1
5.9,3.0,4.2,1.5,1
6.0,2.2,4.0,1.0,1
6.1,2.9,4.7,1.4,1
5.6,2.9,3.6,1.3,1
6.7,3.1,4.4,1.4,1
5.6,3.0,4.5,1.5,1
5.8,2.7,4.1,1.0,1
6.2,2.2,4.5,1.5,1
5.6,2.5,3.9,1.1,1
5.9,3.2,4.8,1.8,1
6.1,2.8,4.0,1.3,1
6.3,2.5,4.9,1.5,1
6.1,2.8,4.7,1.2,1
6.4,2.9,4.3,1.3,1
6.6,3.0,4.4,1.4,1
6.8,2.8,4.8,1.4,1
6.7,3.0,5.0,1.7,1
6.0,2.9,4.5,1.5,1
5.7,2.6,3.5,1.0,1
5.5,2.4,3.8,1.1,1
5.5,2.4,3.7,1.0,1
5.8,2.7,3.9,1.2,1
6.0,2.7,5.1,1.6,1
5.4,3.0,4.5,1.5,1
6.0,3.4,4.5,1.6,1
6.7,3.1,4.7,1.5,1
6.3,2.3,4.4,1.3,1
5.6,3.0,4.1,1.3,1
5.5,2.5,4.0,1.3,1
5.5,2.6,4.4,1.2,1
6.1,3.0,4.6,1.4,1
5.8,2.6,4.0,1.2,1
5.0,2.3,3.3,1.0,1
5.6,2.7,4.2,1.3,1
5.7,3.0,4.2,1.2,1
5.7,2.9,4.2,1.3,1
6.2,2.9,4.3,1.3,1
5.1,2.5,3.0,1.1,1
5.7,2.8,4.1,1.3,1
6.3,3.3,6.0,2.5,2
5.8,2.7,5.1,1.9,2
7.1,3.0,5.9,2.1,2
6.3,2.9,5.6,1.8,2
6.5,3.0,5.8,2.2,2
7.6,3.0,6.6,2.1,2
4.9,2.5,4.5,1.7,2
7.3,2.9,6.3,1.8,2
6.7,2.5,5.8,1.8,2
7.2,3.6,6.1,2.5,2
6.5,3.2,5.1,2.0,2
6.4,2.7,5.3,1.9,2
6.8,3.0,5.5,2.1,2
5.7,2.5,5.0,2.0,2
5.8,2.8,5.1,2.4,2
6.4,3.2,5.3,2.3,2
6.5,3.0,5.5,1.8,2
7.7,3.8,6.7,2.2,2
7.7,2.6,6.9,2.3,2
6.0,2.2,5.0,1.5,2
6.9,3.2,5.7,2.3,2
5.6,2.8,4.9,2.0,2
7.7,2.8,6.7,2.0,2
6.3,2.7,4.9,1.8,2
6.7,3.3,5.7,2.1,2
7.2,3.2,6.0,1.8,2
6.2,2.8,4.8,1.8,2
6.1,3.0,4.9,1.8,2
6.4,2.8,5.6,2.1,2
7.2,3.0,5.8,1.6,2
7.4,2.8,6.1,1.9,2
7.9,3.8,6.4,2.0,2
6.4,2.8,5.6,2.2,2
6.3,2.8,5.1,1.5,2
6.1,2.6,5.6,1.4,2
7.7,3.0,6.1,2.3,2
6.3,3.4,5.6,2.4,2
6.4,3.1,5.5,1.8,2
6.0,3.0,4.8,1.8,2
6.9,3.1,5.4,2.1,2
6.7,3.1,5.6,2.4,2
6.9,3.1,5.1,2.3,2
5.8,2.7,5.1,1.9,2
6.8,3.2,5.9,2.3,2
6.7,3.3,5.7,2.5,2
6.7,3.0,5.2,2.3,2
6.3,2.5,5.0,1.9,2
6.5,3.0,5.2,2.0,2
6.2,3.4,5.4,2.3,2
5.9,3.0,5.1,1.8,2
1 150 4 setosa versicolor virginica
2 5.1 3.5 1.4 0.2 0
3 4.9 3.0 1.4 0.2 0
4 4.7 3.2 1.3 0.2 0
5 4.6 3.1 1.5 0.2 0
6 5.0 3.6 1.4 0.2 0
7 5.4 3.9 1.7 0.4 0
8 4.6 3.4 1.4 0.3 0
9 5.0 3.4 1.5 0.2 0
10 4.4 2.9 1.4 0.2 0
11 4.9 3.1 1.5 0.1 0
12 5.4 3.7 1.5 0.2 0
13 4.8 3.4 1.6 0.2 0
14 4.8 3.0 1.4 0.1 0
15 4.3 3.0 1.1 0.1 0
16 5.8 4.0 1.2 0.2 0
17 5.7 4.4 1.5 0.4 0
18 5.4 3.9 1.3 0.4 0
19 5.1 3.5 1.4 0.3 0
20 5.7 3.8 1.7 0.3 0
21 5.1 3.8 1.5 0.3 0
22 5.4 3.4 1.7 0.2 0
23 5.1 3.7 1.5 0.4 0
24 4.6 3.6 1.0 0.2 0
25 5.1 3.3 1.7 0.5 0
26 4.8 3.4 1.9 0.2 0
27 5.0 3.0 1.6 0.2 0
28 5.0 3.4 1.6 0.4 0
29 5.2 3.5 1.5 0.2 0
30 5.2 3.4 1.4 0.2 0
31 4.7 3.2 1.6 0.2 0
32 4.8 3.1 1.6 0.2 0
33 5.4 3.4 1.5 0.4 0
34 5.2 4.1 1.5 0.1 0
35 5.5 4.2 1.4 0.2 0
36 4.9 3.1 1.5 0.2 0
37 5.0 3.2 1.2 0.2 0
38 5.5 3.5 1.3 0.2 0
39 4.9 3.6 1.4 0.1 0
40 4.4 3.0 1.3 0.2 0
41 5.1 3.4 1.5 0.2 0
42 5.0 3.5 1.3 0.3 0
43 4.5 2.3 1.3 0.3 0
44 4.4 3.2 1.3 0.2 0
45 5.0 3.5 1.6 0.6 0
46 5.1 3.8 1.9 0.4 0
47 4.8 3.0 1.4 0.3 0
48 5.1 3.8 1.6 0.2 0
49 4.6 3.2 1.4 0.2 0
50 5.3 3.7 1.5 0.2 0
51 5.0 3.3 1.4 0.2 0
52 7.0 3.2 4.7 1.4 1
53 6.4 3.2 4.5 1.5 1
54 6.9 3.1 4.9 1.5 1
55 5.5 2.3 4.0 1.3 1
56 6.5 2.8 4.6 1.5 1
57 5.7 2.8 4.5 1.3 1
58 6.3 3.3 4.7 1.6 1
59 4.9 2.4 3.3 1.0 1
60 6.6 2.9 4.6 1.3 1
61 5.2 2.7 3.9 1.4 1
62 5.0 2.0 3.5 1.0 1
63 5.9 3.0 4.2 1.5 1
64 6.0 2.2 4.0 1.0 1
65 6.1 2.9 4.7 1.4 1
66 5.6 2.9 3.6 1.3 1
67 6.7 3.1 4.4 1.4 1
68 5.6 3.0 4.5 1.5 1
69 5.8 2.7 4.1 1.0 1
70 6.2 2.2 4.5 1.5 1
71 5.6 2.5 3.9 1.1 1
72 5.9 3.2 4.8 1.8 1
73 6.1 2.8 4.0 1.3 1
74 6.3 2.5 4.9 1.5 1
75 6.1 2.8 4.7 1.2 1
76 6.4 2.9 4.3 1.3 1
77 6.6 3.0 4.4 1.4 1
78 6.8 2.8 4.8 1.4 1
79 6.7 3.0 5.0 1.7 1
80 6.0 2.9 4.5 1.5 1
81 5.7 2.6 3.5 1.0 1
82 5.5 2.4 3.8 1.1 1
83 5.5 2.4 3.7 1.0 1
84 5.8 2.7 3.9 1.2 1
85 6.0 2.7 5.1 1.6 1
86 5.4 3.0 4.5 1.5 1
87 6.0 3.4 4.5 1.6 1
88 6.7 3.1 4.7 1.5 1
89 6.3 2.3 4.4 1.3 1
90 5.6 3.0 4.1 1.3 1
91 5.5 2.5 4.0 1.3 1
92 5.5 2.6 4.4 1.2 1
93 6.1 3.0 4.6 1.4 1
94 5.8 2.6 4.0 1.2 1
95 5.0 2.3 3.3 1.0 1
96 5.6 2.7 4.2 1.3 1
97 5.7 3.0 4.2 1.2 1
98 5.7 2.9 4.2 1.3 1
99 6.2 2.9 4.3 1.3 1
100 5.1 2.5 3.0 1.1 1
101 5.7 2.8 4.1 1.3 1
102 6.3 3.3 6.0 2.5 2
103 5.8 2.7 5.1 1.9 2
104 7.1 3.0 5.9 2.1 2
105 6.3 2.9 5.6 1.8 2
106 6.5 3.0 5.8 2.2 2
107 7.6 3.0 6.6 2.1 2
108 4.9 2.5 4.5 1.7 2
109 7.3 2.9 6.3 1.8 2
110 6.7 2.5 5.8 1.8 2
111 7.2 3.6 6.1 2.5 2
112 6.5 3.2 5.1 2.0 2
113 6.4 2.7 5.3 1.9 2
114 6.8 3.0 5.5 2.1 2
115 5.7 2.5 5.0 2.0 2
116 5.8 2.8 5.1 2.4 2
117 6.4 3.2 5.3 2.3 2
118 6.5 3.0 5.5 1.8 2
119 7.7 3.8 6.7 2.2 2
120 7.7 2.6 6.9 2.3 2
121 6.0 2.2 5.0 1.5 2
122 6.9 3.2 5.7 2.3 2
123 5.6 2.8 4.9 2.0 2
124 7.7 2.8 6.7 2.0 2
125 6.3 2.7 4.9 1.8 2
126 6.7 3.3 5.7 2.1 2
127 7.2 3.2 6.0 1.8 2
128 6.2 2.8 4.8 1.8 2
129 6.1 3.0 4.9 1.8 2
130 6.4 2.8 5.6 2.1 2
131 7.2 3.0 5.8 1.6 2
132 7.4 2.8 6.1 1.9 2
133 7.9 3.8 6.4 2.0 2
134 6.4 2.8 5.6 2.2 2
135 6.3 2.8 5.1 1.5 2
136 6.1 2.6 5.6 1.4 2
137 7.7 3.0 6.1 2.3 2
138 6.3 3.4 5.6 2.4 2
139 6.4 3.1 5.5 1.8 2
140 6.0 3.0 4.8 1.8 2
141 6.9 3.1 5.4 2.1 2
142 6.7 3.1 5.6 2.4 2
143 6.9 3.1 5.1 2.3 2
144 5.8 2.7 5.1 1.9 2
145 6.8 3.2 5.9 2.3 2
146 6.7 3.3 5.7 2.5 2
147 6.7 3.0 5.2 2.3 2
148 6.3 2.5 5.0 1.9 2
149 6.5 3.0 5.2 2.0 2
150 6.2 3.4 5.4 2.3 2
151 5.9 3.0 5.1 1.8 2
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/data/linnerud_exercise.csv
+21 -21
View File
@@ -1,21 +1,21 @@
Chins Situps Jumps
5 162 60
2 110 60
12 101 101
12 105 37
13 155 58
4 101 42
8 101 38
6 125 40
15 200 40
17 251 250
17 120 38
13 210 115
14 215 105
1 50 50
6 70 31
12 210 120
4 60 25
11 230 80
15 225 73
2 110 43
Chins Situps Jumps
5 162 60
2 110 60
12 101 101
12 105 37
13 155 58
4 101 42
8 101 38
6 125 40
15 200 40
17 251 250
17 120 38
13 210 115
14 215 105
1 50 50
6 70 31
12 210 120
4 60 25
11 230 80
15 225 73
2 110 43
1 Chins Situps Jumps
2 5 162 60
3 2 110 60
4 12 101 101
5 12 105 37
6 13 155 58
7 4 101 42
8 8 101 38
9 6 125 40
10 15 200 40
11 17 251 250
12 17 120 38
13 13 210 115
14 14 215 105
15 1 50 50
16 6 70 31
17 12 210 120
18 4 60 25
19 11 230 80
20 15 225 73
21 2 110 43
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/data/linnerud_physiological.csv
+21 -21
View File
@@ -1,21 +1,21 @@
Weight Waist Pulse
191 36 50
189 37 52
193 38 58
162 35 62
189 35 46
182 36 56
211 38 56
167 34 60
176 31 74
154 33 56
169 34 50
166 33 52
154 34 64
247 46 50
193 36 46
202 37 62
176 37 54
157 32 52
156 33 54
138 33 68
Weight Waist Pulse
191 36 50
189 37 52
193 38 58
162 35 62
189 35 46
182 36 56
211 38 56
167 34 60
176 31 74
154 33 56
169 34 50
166 33 52
154 34 64
247 46 50
193 36 46
202 37 62
176 37 54
157 32 52
156 33 54
138 33 68
1 Weight Waist Pulse
2 191 36 50
3 189 37 52
4 193 38 58
5 162 35 62
6 189 35 46
7 182 36 56
8 211 38 56
9 167 34 60
10 176 31 74
11 154 33 56
12 169 34 50
13 166 33 52
14 154 34 64
15 247 46 50
16 193 36 46
17 202 37 62
18 176 37 54
19 157 32 52
20 156 33 54
21 138 33 68
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/data/wine_data.csv
+179 -179
View File
@@ -1,179 +1,179 @@
178,13,class_0,class_1,class_2
14.23,1.71,2.43,15.6,127,2.8,3.06,0.28,2.29,5.64,1.04,3.92,1065,0
13.2,1.78,2.14,11.2,100,2.65,2.76,0.26,1.28,4.38,1.05,3.4,1050,0
13.16,2.36,2.67,18.6,101,2.8,3.24,0.3,2.81,5.68,1.03,3.17,1185,0
14.37,1.95,2.5,16.8,113,3.85,3.49,0.24,2.18,7.8,0.86,3.45,1480,0
13.24,2.59,2.87,21,118,2.8,2.69,0.39,1.82,4.32,1.04,2.93,735,0
14.2,1.76,2.45,15.2,112,3.27,3.39,0.34,1.97,6.75,1.05,2.85,1450,0
14.39,1.87,2.45,14.6,96,2.5,2.52,0.3,1.98,5.25,1.02,3.58,1290,0
14.06,2.15,2.61,17.6,121,2.6,2.51,0.31,1.25,5.05,1.06,3.58,1295,0
14.83,1.64,2.17,14,97,2.8,2.98,0.29,1.98,5.2,1.08,2.85,1045,0
13.86,1.35,2.27,16,98,2.98,3.15,0.22,1.85,7.22,1.01,3.55,1045,0
14.1,2.16,2.3,18,105,2.95,3.32,0.22,2.38,5.75,1.25,3.17,1510,0
14.12,1.48,2.32,16.8,95,2.2,2.43,0.26,1.57,5,1.17,2.82,1280,0
13.75,1.73,2.41,16,89,2.6,2.76,0.29,1.81,5.6,1.15,2.9,1320,0
14.75,1.73,2.39,11.4,91,3.1,3.69,0.43,2.81,5.4,1.25,2.73,1150,0
14.38,1.87,2.38,12,102,3.3,3.64,0.29,2.96,7.5,1.2,3,1547,0
13.63,1.81,2.7,17.2,112,2.85,2.91,0.3,1.46,7.3,1.28,2.88,1310,0
14.3,1.92,2.72,20,120,2.8,3.14,0.33,1.97,6.2,1.07,2.65,1280,0
13.83,1.57,2.62,20,115,2.95,3.4,0.4,1.72,6.6,1.13,2.57,1130,0
14.19,1.59,2.48,16.5,108,3.3,3.93,0.32,1.86,8.7,1.23,2.82,1680,0
13.64,3.1,2.56,15.2,116,2.7,3.03,0.17,1.66,5.1,0.96,3.36,845,0
14.06,1.63,2.28,16,126,3,3.17,0.24,2.1,5.65,1.09,3.71,780,0
12.93,3.8,2.65,18.6,102,2.41,2.41,0.25,1.98,4.5,1.03,3.52,770,0
13.71,1.86,2.36,16.6,101,2.61,2.88,0.27,1.69,3.8,1.11,4,1035,0
12.85,1.6,2.52,17.8,95,2.48,2.37,0.26,1.46,3.93,1.09,3.63,1015,0
13.5,1.81,2.61,20,96,2.53,2.61,0.28,1.66,3.52,1.12,3.82,845,0
13.05,2.05,3.22,25,124,2.63,2.68,0.47,1.92,3.58,1.13,3.2,830,0
13.39,1.77,2.62,16.1,93,2.85,2.94,0.34,1.45,4.8,0.92,3.22,1195,0
13.3,1.72,2.14,17,94,2.4,2.19,0.27,1.35,3.95,1.02,2.77,1285,0
13.87,1.9,2.8,19.4,107,2.95,2.97,0.37,1.76,4.5,1.25,3.4,915,0
14.02,1.68,2.21,16,96,2.65,2.33,0.26,1.98,4.7,1.04,3.59,1035,0
13.73,1.5,2.7,22.5,101,3,3.25,0.29,2.38,5.7,1.19,2.71,1285,0
13.58,1.66,2.36,19.1,106,2.86,3.19,0.22,1.95,6.9,1.09,2.88,1515,0
13.68,1.83,2.36,17.2,104,2.42,2.69,0.42,1.97,3.84,1.23,2.87,990,0
13.76,1.53,2.7,19.5,132,2.95,2.74,0.5,1.35,5.4,1.25,3,1235,0
13.51,1.8,2.65,19,110,2.35,2.53,0.29,1.54,4.2,1.1,2.87,1095,0
13.48,1.81,2.41,20.5,100,2.7,2.98,0.26,1.86,5.1,1.04,3.47,920,0
13.28,1.64,2.84,15.5,110,2.6,2.68,0.34,1.36,4.6,1.09,2.78,880,0
13.05,1.65,2.55,18,98,2.45,2.43,0.29,1.44,4.25,1.12,2.51,1105,0
13.07,1.5,2.1,15.5,98,2.4,2.64,0.28,1.37,3.7,1.18,2.69,1020,0
14.22,3.99,2.51,13.2,128,3,3.04,0.2,2.08,5.1,0.89,3.53,760,0
13.56,1.71,2.31,16.2,117,3.15,3.29,0.34,2.34,6.13,0.95,3.38,795,0
13.41,3.84,2.12,18.8,90,2.45,2.68,0.27,1.48,4.28,0.91,3,1035,0
13.88,1.89,2.59,15,101,3.25,3.56,0.17,1.7,5.43,0.88,3.56,1095,0
13.24,3.98,2.29,17.5,103,2.64,2.63,0.32,1.66,4.36,0.82,3,680,0
13.05,1.77,2.1,17,107,3,3,0.28,2.03,5.04,0.88,3.35,885,0
14.21,4.04,2.44,18.9,111,2.85,2.65,0.3,1.25,5.24,0.87,3.33,1080,0
14.38,3.59,2.28,16,102,3.25,3.17,0.27,2.19,4.9,1.04,3.44,1065,0
13.9,1.68,2.12,16,101,3.1,3.39,0.21,2.14,6.1,0.91,3.33,985,0
14.1,2.02,2.4,18.8,103,2.75,2.92,0.32,2.38,6.2,1.07,2.75,1060,0
13.94,1.73,2.27,17.4,108,2.88,3.54,0.32,2.08,8.9,1.12,3.1,1260,0
13.05,1.73,2.04,12.4,92,2.72,3.27,0.17,2.91,7.2,1.12,2.91,1150,0
13.83,1.65,2.6,17.2,94,2.45,2.99,0.22,2.29,5.6,1.24,3.37,1265,0
13.82,1.75,2.42,14,111,3.88,3.74,0.32,1.87,7.05,1.01,3.26,1190,0
13.77,1.9,2.68,17.1,115,3,2.79,0.39,1.68,6.3,1.13,2.93,1375,0
13.74,1.67,2.25,16.4,118,2.6,2.9,0.21,1.62,5.85,0.92,3.2,1060,0
13.56,1.73,2.46,20.5,116,2.96,2.78,0.2,2.45,6.25,0.98,3.03,1120,0
14.22,1.7,2.3,16.3,118,3.2,3,0.26,2.03,6.38,0.94,3.31,970,0
13.29,1.97,2.68,16.8,102,3,3.23,0.31,1.66,6,1.07,2.84,1270,0
13.72,1.43,2.5,16.7,108,3.4,3.67,0.19,2.04,6.8,0.89,2.87,1285,0
12.37,0.94,1.36,10.6,88,1.98,0.57,0.28,0.42,1.95,1.05,1.82,520,1
12.33,1.1,2.28,16,101,2.05,1.09,0.63,0.41,3.27,1.25,1.67,680,1
12.64,1.36,2.02,16.8,100,2.02,1.41,0.53,0.62,5.75,0.98,1.59,450,1
13.67,1.25,1.92,18,94,2.1,1.79,0.32,0.73,3.8,1.23,2.46,630,1
12.37,1.13,2.16,19,87,3.5,3.1,0.19,1.87,4.45,1.22,2.87,420,1
12.17,1.45,2.53,19,104,1.89,1.75,0.45,1.03,2.95,1.45,2.23,355,1
12.37,1.21,2.56,18.1,98,2.42,2.65,0.37,2.08,4.6,1.19,2.3,678,1
13.11,1.01,1.7,15,78,2.98,3.18,0.26,2.28,5.3,1.12,3.18,502,1
12.37,1.17,1.92,19.6,78,2.11,2,0.27,1.04,4.68,1.12,3.48,510,1
13.34,0.94,2.36,17,110,2.53,1.3,0.55,0.42,3.17,1.02,1.93,750,1
12.21,1.19,1.75,16.8,151,1.85,1.28,0.14,2.5,2.85,1.28,3.07,718,1
12.29,1.61,2.21,20.4,103,1.1,1.02,0.37,1.46,3.05,0.906,1.82,870,1
13.86,1.51,2.67,25,86,2.95,2.86,0.21,1.87,3.38,1.36,3.16,410,1
13.49,1.66,2.24,24,87,1.88,1.84,0.27,1.03,3.74,0.98,2.78,472,1
12.99,1.67,2.6,30,139,3.3,2.89,0.21,1.96,3.35,1.31,3.5,985,1
11.96,1.09,2.3,21,101,3.38,2.14,0.13,1.65,3.21,0.99,3.13,886,1
11.66,1.88,1.92,16,97,1.61,1.57,0.34,1.15,3.8,1.23,2.14,428,1
13.03,0.9,1.71,16,86,1.95,2.03,0.24,1.46,4.6,1.19,2.48,392,1
11.84,2.89,2.23,18,112,1.72,1.32,0.43,0.95,2.65,0.96,2.52,500,1
12.33,0.99,1.95,14.8,136,1.9,1.85,0.35,2.76,3.4,1.06,2.31,750,1
12.7,3.87,2.4,23,101,2.83,2.55,0.43,1.95,2.57,1.19,3.13,463,1
12,0.92,2,19,86,2.42,2.26,0.3,1.43,2.5,1.38,3.12,278,1
12.72,1.81,2.2,18.8,86,2.2,2.53,0.26,1.77,3.9,1.16,3.14,714,1
12.08,1.13,2.51,24,78,2,1.58,0.4,1.4,2.2,1.31,2.72,630,1
13.05,3.86,2.32,22.5,85,1.65,1.59,0.61,1.62,4.8,0.84,2.01,515,1
11.84,0.89,2.58,18,94,2.2,2.21,0.22,2.35,3.05,0.79,3.08,520,1
12.67,0.98,2.24,18,99,2.2,1.94,0.3,1.46,2.62,1.23,3.16,450,1
12.16,1.61,2.31,22.8,90,1.78,1.69,0.43,1.56,2.45,1.33,2.26,495,1
11.65,1.67,2.62,26,88,1.92,1.61,0.4,1.34,2.6,1.36,3.21,562,1
11.64,2.06,2.46,21.6,84,1.95,1.69,0.48,1.35,2.8,1,2.75,680,1
12.08,1.33,2.3,23.6,70,2.2,1.59,0.42,1.38,1.74,1.07,3.21,625,1
12.08,1.83,2.32,18.5,81,1.6,1.5,0.52,1.64,2.4,1.08,2.27,480,1
12,1.51,2.42,22,86,1.45,1.25,0.5,1.63,3.6,1.05,2.65,450,1
12.69,1.53,2.26,20.7,80,1.38,1.46,0.58,1.62,3.05,0.96,2.06,495,1
12.29,2.83,2.22,18,88,2.45,2.25,0.25,1.99,2.15,1.15,3.3,290,1
11.62,1.99,2.28,18,98,3.02,2.26,0.17,1.35,3.25,1.16,2.96,345,1
12.47,1.52,2.2,19,162,2.5,2.27,0.32,3.28,2.6,1.16,2.63,937,1
11.81,2.12,2.74,21.5,134,1.6,0.99,0.14,1.56,2.5,0.95,2.26,625,1
12.29,1.41,1.98,16,85,2.55,2.5,0.29,1.77,2.9,1.23,2.74,428,1
12.37,1.07,2.1,18.5,88,3.52,3.75,0.24,1.95,4.5,1.04,2.77,660,1
12.29,3.17,2.21,18,88,2.85,2.99,0.45,2.81,2.3,1.42,2.83,406,1
12.08,2.08,1.7,17.5,97,2.23,2.17,0.26,1.4,3.3,1.27,2.96,710,1
12.6,1.34,1.9,18.5,88,1.45,1.36,0.29,1.35,2.45,1.04,2.77,562,1
12.34,2.45,2.46,21,98,2.56,2.11,0.34,1.31,2.8,0.8,3.38,438,1
11.82,1.72,1.88,19.5,86,2.5,1.64,0.37,1.42,2.06,0.94,2.44,415,1
12.51,1.73,1.98,20.5,85,2.2,1.92,0.32,1.48,2.94,1.04,3.57,672,1
12.42,2.55,2.27,22,90,1.68,1.84,0.66,1.42,2.7,0.86,3.3,315,1
12.25,1.73,2.12,19,80,1.65,2.03,0.37,1.63,3.4,1,3.17,510,1
12.72,1.75,2.28,22.5,84,1.38,1.76,0.48,1.63,3.3,0.88,2.42,488,1
12.22,1.29,1.94,19,92,2.36,2.04,0.39,2.08,2.7,0.86,3.02,312,1
11.61,1.35,2.7,20,94,2.74,2.92,0.29,2.49,2.65,0.96,3.26,680,1
11.46,3.74,1.82,19.5,107,3.18,2.58,0.24,3.58,2.9,0.75,2.81,562,1
12.52,2.43,2.17,21,88,2.55,2.27,0.26,1.22,2,0.9,2.78,325,1
11.76,2.68,2.92,20,103,1.75,2.03,0.6,1.05,3.8,1.23,2.5,607,1
11.41,0.74,2.5,21,88,2.48,2.01,0.42,1.44,3.08,1.1,2.31,434,1
12.08,1.39,2.5,22.5,84,2.56,2.29,0.43,1.04,2.9,0.93,3.19,385,1
11.03,1.51,2.2,21.5,85,2.46,2.17,0.52,2.01,1.9,1.71,2.87,407,1
11.82,1.47,1.99,20.8,86,1.98,1.6,0.3,1.53,1.95,0.95,3.33,495,1
12.42,1.61,2.19,22.5,108,2,2.09,0.34,1.61,2.06,1.06,2.96,345,1
12.77,3.43,1.98,16,80,1.63,1.25,0.43,0.83,3.4,0.7,2.12,372,1
12,3.43,2,19,87,2,1.64,0.37,1.87,1.28,0.93,3.05,564,1
11.45,2.4,2.42,20,96,2.9,2.79,0.32,1.83,3.25,0.8,3.39,625,1
11.56,2.05,3.23,28.5,119,3.18,5.08,0.47,1.87,6,0.93,3.69,465,1
12.42,4.43,2.73,26.5,102,2.2,2.13,0.43,1.71,2.08,0.92,3.12,365,1
13.05,5.8,2.13,21.5,86,2.62,2.65,0.3,2.01,2.6,0.73,3.1,380,1
11.87,4.31,2.39,21,82,2.86,3.03,0.21,2.91,2.8,0.75,3.64,380,1
12.07,2.16,2.17,21,85,2.6,2.65,0.37,1.35,2.76,0.86,3.28,378,1
12.43,1.53,2.29,21.5,86,2.74,3.15,0.39,1.77,3.94,0.69,2.84,352,1
11.79,2.13,2.78,28.5,92,2.13,2.24,0.58,1.76,3,0.97,2.44,466,1
12.37,1.63,2.3,24.5,88,2.22,2.45,0.4,1.9,2.12,0.89,2.78,342,1
12.04,4.3,2.38,22,80,2.1,1.75,0.42,1.35,2.6,0.79,2.57,580,1
12.86,1.35,2.32,18,122,1.51,1.25,0.21,0.94,4.1,0.76,1.29,630,2
12.88,2.99,2.4,20,104,1.3,1.22,0.24,0.83,5.4,0.74,1.42,530,2
12.81,2.31,2.4,24,98,1.15,1.09,0.27,0.83,5.7,0.66,1.36,560,2
12.7,3.55,2.36,21.5,106,1.7,1.2,0.17,0.84,5,0.78,1.29,600,2
12.51,1.24,2.25,17.5,85,2,0.58,0.6,1.25,5.45,0.75,1.51,650,2
12.6,2.46,2.2,18.5,94,1.62,0.66,0.63,0.94,7.1,0.73,1.58,695,2
12.25,4.72,2.54,21,89,1.38,0.47,0.53,0.8,3.85,0.75,1.27,720,2
12.53,5.51,2.64,25,96,1.79,0.6,0.63,1.1,5,0.82,1.69,515,2
13.49,3.59,2.19,19.5,88,1.62,0.48,0.58,0.88,5.7,0.81,1.82,580,2
12.84,2.96,2.61,24,101,2.32,0.6,0.53,0.81,4.92,0.89,2.15,590,2
12.93,2.81,2.7,21,96,1.54,0.5,0.53,0.75,4.6,0.77,2.31,600,2
13.36,2.56,2.35,20,89,1.4,0.5,0.37,0.64,5.6,0.7,2.47,780,2
13.52,3.17,2.72,23.5,97,1.55,0.52,0.5,0.55,4.35,0.89,2.06,520,2
13.62,4.95,2.35,20,92,2,0.8,0.47,1.02,4.4,0.91,2.05,550,2
12.25,3.88,2.2,18.5,112,1.38,0.78,0.29,1.14,8.21,0.65,2,855,2
13.16,3.57,2.15,21,102,1.5,0.55,0.43,1.3,4,0.6,1.68,830,2
13.88,5.04,2.23,20,80,0.98,0.34,0.4,0.68,4.9,0.58,1.33,415,2
12.87,4.61,2.48,21.5,86,1.7,0.65,0.47,0.86,7.65,0.54,1.86,625,2
13.32,3.24,2.38,21.5,92,1.93,0.76,0.45,1.25,8.42,0.55,1.62,650,2
13.08,3.9,2.36,21.5,113,1.41,1.39,0.34,1.14,9.4,0.57,1.33,550,2
13.5,3.12,2.62,24,123,1.4,1.57,0.22,1.25,8.6,0.59,1.3,500,2
12.79,2.67,2.48,22,112,1.48,1.36,0.24,1.26,10.8,0.48,1.47,480,2
13.11,1.9,2.75,25.5,116,2.2,1.28,0.26,1.56,7.1,0.61,1.33,425,2
13.23,3.3,2.28,18.5,98,1.8,0.83,0.61,1.87,10.52,0.56,1.51,675,2
12.58,1.29,2.1,20,103,1.48,0.58,0.53,1.4,7.6,0.58,1.55,640,2
13.17,5.19,2.32,22,93,1.74,0.63,0.61,1.55,7.9,0.6,1.48,725,2
13.84,4.12,2.38,19.5,89,1.8,0.83,0.48,1.56,9.01,0.57,1.64,480,2
12.45,3.03,2.64,27,97,1.9,0.58,0.63,1.14,7.5,0.67,1.73,880,2
14.34,1.68,2.7,25,98,2.8,1.31,0.53,2.7,13,0.57,1.96,660,2
13.48,1.67,2.64,22.5,89,2.6,1.1,0.52,2.29,11.75,0.57,1.78,620,2
12.36,3.83,2.38,21,88,2.3,0.92,0.5,1.04,7.65,0.56,1.58,520,2
13.69,3.26,2.54,20,107,1.83,0.56,0.5,0.8,5.88,0.96,1.82,680,2
12.85,3.27,2.58,22,106,1.65,0.6,0.6,0.96,5.58,0.87,2.11,570,2
12.96,3.45,2.35,18.5,106,1.39,0.7,0.4,0.94,5.28,0.68,1.75,675,2
13.78,2.76,2.3,22,90,1.35,0.68,0.41,1.03,9.58,0.7,1.68,615,2
13.73,4.36,2.26,22.5,88,1.28,0.47,0.52,1.15,6.62,0.78,1.75,520,2
13.45,3.7,2.6,23,111,1.7,0.92,0.43,1.46,10.68,0.85,1.56,695,2
12.82,3.37,2.3,19.5,88,1.48,0.66,0.4,0.97,10.26,0.72,1.75,685,2
13.58,2.58,2.69,24.5,105,1.55,0.84,0.39,1.54,8.66,0.74,1.8,750,2
13.4,4.6,2.86,25,112,1.98,0.96,0.27,1.11,8.5,0.67,1.92,630,2
12.2,3.03,2.32,19,96,1.25,0.49,0.4,0.73,5.5,0.66,1.83,510,2
12.77,2.39,2.28,19.5,86,1.39,0.51,0.48,0.64,9.899999,0.57,1.63,470,2
14.16,2.51,2.48,20,91,1.68,0.7,0.44,1.24,9.7,0.62,1.71,660,2
13.71,5.65,2.45,20.5,95,1.68,0.61,0.52,1.06,7.7,0.64,1.74,740,2
13.4,3.91,2.48,23,102,1.8,0.75,0.43,1.41,7.3,0.7,1.56,750,2
13.27,4.28,2.26,20,120,1.59,0.69,0.43,1.35,10.2,0.59,1.56,835,2
13.17,2.59,2.37,20,120,1.65,0.68,0.53,1.46,9.3,0.6,1.62,840,2
14.13,4.1,2.74,24.5,96,2.05,0.76,0.56,1.35,9.2,0.61,1.6,560,2
178,13,class_0,class_1,class_2
14.23,1.71,2.43,15.6,127,2.8,3.06,0.28,2.29,5.64,1.04,3.92,1065,0
13.2,1.78,2.14,11.2,100,2.65,2.76,0.26,1.28,4.38,1.05,3.4,1050,0
13.16,2.36,2.67,18.6,101,2.8,3.24,0.3,2.81,5.68,1.03,3.17,1185,0
14.37,1.95,2.5,16.8,113,3.85,3.49,0.24,2.18,7.8,0.86,3.45,1480,0
13.24,2.59,2.87,21,118,2.8,2.69,0.39,1.82,4.32,1.04,2.93,735,0
14.2,1.76,2.45,15.2,112,3.27,3.39,0.34,1.97,6.75,1.05,2.85,1450,0
14.39,1.87,2.45,14.6,96,2.5,2.52,0.3,1.98,5.25,1.02,3.58,1290,0
14.06,2.15,2.61,17.6,121,2.6,2.51,0.31,1.25,5.05,1.06,3.58,1295,0
14.83,1.64,2.17,14,97,2.8,2.98,0.29,1.98,5.2,1.08,2.85,1045,0
13.86,1.35,2.27,16,98,2.98,3.15,0.22,1.85,7.22,1.01,3.55,1045,0
14.1,2.16,2.3,18,105,2.95,3.32,0.22,2.38,5.75,1.25,3.17,1510,0
14.12,1.48,2.32,16.8,95,2.2,2.43,0.26,1.57,5,1.17,2.82,1280,0
13.75,1.73,2.41,16,89,2.6,2.76,0.29,1.81,5.6,1.15,2.9,1320,0
14.75,1.73,2.39,11.4,91,3.1,3.69,0.43,2.81,5.4,1.25,2.73,1150,0
14.38,1.87,2.38,12,102,3.3,3.64,0.29,2.96,7.5,1.2,3,1547,0
13.63,1.81,2.7,17.2,112,2.85,2.91,0.3,1.46,7.3,1.28,2.88,1310,0
14.3,1.92,2.72,20,120,2.8,3.14,0.33,1.97,6.2,1.07,2.65,1280,0
13.83,1.57,2.62,20,115,2.95,3.4,0.4,1.72,6.6,1.13,2.57,1130,0
14.19,1.59,2.48,16.5,108,3.3,3.93,0.32,1.86,8.7,1.23,2.82,1680,0
13.64,3.1,2.56,15.2,116,2.7,3.03,0.17,1.66,5.1,0.96,3.36,845,0
14.06,1.63,2.28,16,126,3,3.17,0.24,2.1,5.65,1.09,3.71,780,0
12.93,3.8,2.65,18.6,102,2.41,2.41,0.25,1.98,4.5,1.03,3.52,770,0
13.71,1.86,2.36,16.6,101,2.61,2.88,0.27,1.69,3.8,1.11,4,1035,0
12.85,1.6,2.52,17.8,95,2.48,2.37,0.26,1.46,3.93,1.09,3.63,1015,0
13.5,1.81,2.61,20,96,2.53,2.61,0.28,1.66,3.52,1.12,3.82,845,0
13.05,2.05,3.22,25,124,2.63,2.68,0.47,1.92,3.58,1.13,3.2,830,0
13.39,1.77,2.62,16.1,93,2.85,2.94,0.34,1.45,4.8,0.92,3.22,1195,0
13.3,1.72,2.14,17,94,2.4,2.19,0.27,1.35,3.95,1.02,2.77,1285,0
13.87,1.9,2.8,19.4,107,2.95,2.97,0.37,1.76,4.5,1.25,3.4,915,0
14.02,1.68,2.21,16,96,2.65,2.33,0.26,1.98,4.7,1.04,3.59,1035,0
13.73,1.5,2.7,22.5,101,3,3.25,0.29,2.38,5.7,1.19,2.71,1285,0
13.58,1.66,2.36,19.1,106,2.86,3.19,0.22,1.95,6.9,1.09,2.88,1515,0
13.68,1.83,2.36,17.2,104,2.42,2.69,0.42,1.97,3.84,1.23,2.87,990,0
13.76,1.53,2.7,19.5,132,2.95,2.74,0.5,1.35,5.4,1.25,3,1235,0
13.51,1.8,2.65,19,110,2.35,2.53,0.29,1.54,4.2,1.1,2.87,1095,0
13.48,1.81,2.41,20.5,100,2.7,2.98,0.26,1.86,5.1,1.04,3.47,920,0
13.28,1.64,2.84,15.5,110,2.6,2.68,0.34,1.36,4.6,1.09,2.78,880,0
13.05,1.65,2.55,18,98,2.45,2.43,0.29,1.44,4.25,1.12,2.51,1105,0
13.07,1.5,2.1,15.5,98,2.4,2.64,0.28,1.37,3.7,1.18,2.69,1020,0
14.22,3.99,2.51,13.2,128,3,3.04,0.2,2.08,5.1,0.89,3.53,760,0
13.56,1.71,2.31,16.2,117,3.15,3.29,0.34,2.34,6.13,0.95,3.38,795,0
13.41,3.84,2.12,18.8,90,2.45,2.68,0.27,1.48,4.28,0.91,3,1035,0
13.88,1.89,2.59,15,101,3.25,3.56,0.17,1.7,5.43,0.88,3.56,1095,0
13.24,3.98,2.29,17.5,103,2.64,2.63,0.32,1.66,4.36,0.82,3,680,0
13.05,1.77,2.1,17,107,3,3,0.28,2.03,5.04,0.88,3.35,885,0
14.21,4.04,2.44,18.9,111,2.85,2.65,0.3,1.25,5.24,0.87,3.33,1080,0
14.38,3.59,2.28,16,102,3.25,3.17,0.27,2.19,4.9,1.04,3.44,1065,0
13.9,1.68,2.12,16,101,3.1,3.39,0.21,2.14,6.1,0.91,3.33,985,0
14.1,2.02,2.4,18.8,103,2.75,2.92,0.32,2.38,6.2,1.07,2.75,1060,0
13.94,1.73,2.27,17.4,108,2.88,3.54,0.32,2.08,8.9,1.12,3.1,1260,0
13.05,1.73,2.04,12.4,92,2.72,3.27,0.17,2.91,7.2,1.12,2.91,1150,0
13.83,1.65,2.6,17.2,94,2.45,2.99,0.22,2.29,5.6,1.24,3.37,1265,0
13.82,1.75,2.42,14,111,3.88,3.74,0.32,1.87,7.05,1.01,3.26,1190,0
13.77,1.9,2.68,17.1,115,3,2.79,0.39,1.68,6.3,1.13,2.93,1375,0
13.74,1.67,2.25,16.4,118,2.6,2.9,0.21,1.62,5.85,0.92,3.2,1060,0
13.56,1.73,2.46,20.5,116,2.96,2.78,0.2,2.45,6.25,0.98,3.03,1120,0
14.22,1.7,2.3,16.3,118,3.2,3,0.26,2.03,6.38,0.94,3.31,970,0
13.29,1.97,2.68,16.8,102,3,3.23,0.31,1.66,6,1.07,2.84,1270,0
13.72,1.43,2.5,16.7,108,3.4,3.67,0.19,2.04,6.8,0.89,2.87,1285,0
12.37,0.94,1.36,10.6,88,1.98,0.57,0.28,0.42,1.95,1.05,1.82,520,1
12.33,1.1,2.28,16,101,2.05,1.09,0.63,0.41,3.27,1.25,1.67,680,1
12.64,1.36,2.02,16.8,100,2.02,1.41,0.53,0.62,5.75,0.98,1.59,450,1
13.67,1.25,1.92,18,94,2.1,1.79,0.32,0.73,3.8,1.23,2.46,630,1
12.37,1.13,2.16,19,87,3.5,3.1,0.19,1.87,4.45,1.22,2.87,420,1
12.17,1.45,2.53,19,104,1.89,1.75,0.45,1.03,2.95,1.45,2.23,355,1
12.37,1.21,2.56,18.1,98,2.42,2.65,0.37,2.08,4.6,1.19,2.3,678,1
13.11,1.01,1.7,15,78,2.98,3.18,0.26,2.28,5.3,1.12,3.18,502,1
12.37,1.17,1.92,19.6,78,2.11,2,0.27,1.04,4.68,1.12,3.48,510,1
13.34,0.94,2.36,17,110,2.53,1.3,0.55,0.42,3.17,1.02,1.93,750,1
12.21,1.19,1.75,16.8,151,1.85,1.28,0.14,2.5,2.85,1.28,3.07,718,1
12.29,1.61,2.21,20.4,103,1.1,1.02,0.37,1.46,3.05,0.906,1.82,870,1
13.86,1.51,2.67,25,86,2.95,2.86,0.21,1.87,3.38,1.36,3.16,410,1
13.49,1.66,2.24,24,87,1.88,1.84,0.27,1.03,3.74,0.98,2.78,472,1
12.99,1.67,2.6,30,139,3.3,2.89,0.21,1.96,3.35,1.31,3.5,985,1
11.96,1.09,2.3,21,101,3.38,2.14,0.13,1.65,3.21,0.99,3.13,886,1
11.66,1.88,1.92,16,97,1.61,1.57,0.34,1.15,3.8,1.23,2.14,428,1
13.03,0.9,1.71,16,86,1.95,2.03,0.24,1.46,4.6,1.19,2.48,392,1
11.84,2.89,2.23,18,112,1.72,1.32,0.43,0.95,2.65,0.96,2.52,500,1
12.33,0.99,1.95,14.8,136,1.9,1.85,0.35,2.76,3.4,1.06,2.31,750,1
12.7,3.87,2.4,23,101,2.83,2.55,0.43,1.95,2.57,1.19,3.13,463,1
12,0.92,2,19,86,2.42,2.26,0.3,1.43,2.5,1.38,3.12,278,1
12.72,1.81,2.2,18.8,86,2.2,2.53,0.26,1.77,3.9,1.16,3.14,714,1
12.08,1.13,2.51,24,78,2,1.58,0.4,1.4,2.2,1.31,2.72,630,1
13.05,3.86,2.32,22.5,85,1.65,1.59,0.61,1.62,4.8,0.84,2.01,515,1
11.84,0.89,2.58,18,94,2.2,2.21,0.22,2.35,3.05,0.79,3.08,520,1
12.67,0.98,2.24,18,99,2.2,1.94,0.3,1.46,2.62,1.23,3.16,450,1
12.16,1.61,2.31,22.8,90,1.78,1.69,0.43,1.56,2.45,1.33,2.26,495,1
11.65,1.67,2.62,26,88,1.92,1.61,0.4,1.34,2.6,1.36,3.21,562,1
11.64,2.06,2.46,21.6,84,1.95,1.69,0.48,1.35,2.8,1,2.75,680,1
12.08,1.33,2.3,23.6,70,2.2,1.59,0.42,1.38,1.74,1.07,3.21,625,1
12.08,1.83,2.32,18.5,81,1.6,1.5,0.52,1.64,2.4,1.08,2.27,480,1
12,1.51,2.42,22,86,1.45,1.25,0.5,1.63,3.6,1.05,2.65,450,1
12.69,1.53,2.26,20.7,80,1.38,1.46,0.58,1.62,3.05,0.96,2.06,495,1
12.29,2.83,2.22,18,88,2.45,2.25,0.25,1.99,2.15,1.15,3.3,290,1
11.62,1.99,2.28,18,98,3.02,2.26,0.17,1.35,3.25,1.16,2.96,345,1
12.47,1.52,2.2,19,162,2.5,2.27,0.32,3.28,2.6,1.16,2.63,937,1
11.81,2.12,2.74,21.5,134,1.6,0.99,0.14,1.56,2.5,0.95,2.26,625,1
12.29,1.41,1.98,16,85,2.55,2.5,0.29,1.77,2.9,1.23,2.74,428,1
12.37,1.07,2.1,18.5,88,3.52,3.75,0.24,1.95,4.5,1.04,2.77,660,1
12.29,3.17,2.21,18,88,2.85,2.99,0.45,2.81,2.3,1.42,2.83,406,1
12.08,2.08,1.7,17.5,97,2.23,2.17,0.26,1.4,3.3,1.27,2.96,710,1
12.6,1.34,1.9,18.5,88,1.45,1.36,0.29,1.35,2.45,1.04,2.77,562,1
12.34,2.45,2.46,21,98,2.56,2.11,0.34,1.31,2.8,0.8,3.38,438,1
11.82,1.72,1.88,19.5,86,2.5,1.64,0.37,1.42,2.06,0.94,2.44,415,1
12.51,1.73,1.98,20.5,85,2.2,1.92,0.32,1.48,2.94,1.04,3.57,672,1
12.42,2.55,2.27,22,90,1.68,1.84,0.66,1.42,2.7,0.86,3.3,315,1
12.25,1.73,2.12,19,80,1.65,2.03,0.37,1.63,3.4,1,3.17,510,1
12.72,1.75,2.28,22.5,84,1.38,1.76,0.48,1.63,3.3,0.88,2.42,488,1
12.22,1.29,1.94,19,92,2.36,2.04,0.39,2.08,2.7,0.86,3.02,312,1
11.61,1.35,2.7,20,94,2.74,2.92,0.29,2.49,2.65,0.96,3.26,680,1
11.46,3.74,1.82,19.5,107,3.18,2.58,0.24,3.58,2.9,0.75,2.81,562,1
12.52,2.43,2.17,21,88,2.55,2.27,0.26,1.22,2,0.9,2.78,325,1
11.76,2.68,2.92,20,103,1.75,2.03,0.6,1.05,3.8,1.23,2.5,607,1
11.41,0.74,2.5,21,88,2.48,2.01,0.42,1.44,3.08,1.1,2.31,434,1
12.08,1.39,2.5,22.5,84,2.56,2.29,0.43,1.04,2.9,0.93,3.19,385,1
11.03,1.51,2.2,21.5,85,2.46,2.17,0.52,2.01,1.9,1.71,2.87,407,1
11.82,1.47,1.99,20.8,86,1.98,1.6,0.3,1.53,1.95,0.95,3.33,495,1
12.42,1.61,2.19,22.5,108,2,2.09,0.34,1.61,2.06,1.06,2.96,345,1
12.77,3.43,1.98,16,80,1.63,1.25,0.43,0.83,3.4,0.7,2.12,372,1
12,3.43,2,19,87,2,1.64,0.37,1.87,1.28,0.93,3.05,564,1
11.45,2.4,2.42,20,96,2.9,2.79,0.32,1.83,3.25,0.8,3.39,625,1
11.56,2.05,3.23,28.5,119,3.18,5.08,0.47,1.87,6,0.93,3.69,465,1
12.42,4.43,2.73,26.5,102,2.2,2.13,0.43,1.71,2.08,0.92,3.12,365,1
13.05,5.8,2.13,21.5,86,2.62,2.65,0.3,2.01,2.6,0.73,3.1,380,1
11.87,4.31,2.39,21,82,2.86,3.03,0.21,2.91,2.8,0.75,3.64,380,1
12.07,2.16,2.17,21,85,2.6,2.65,0.37,1.35,2.76,0.86,3.28,378,1
12.43,1.53,2.29,21.5,86,2.74,3.15,0.39,1.77,3.94,0.69,2.84,352,1
11.79,2.13,2.78,28.5,92,2.13,2.24,0.58,1.76,3,0.97,2.44,466,1
12.37,1.63,2.3,24.5,88,2.22,2.45,0.4,1.9,2.12,0.89,2.78,342,1
12.04,4.3,2.38,22,80,2.1,1.75,0.42,1.35,2.6,0.79,2.57,580,1
12.86,1.35,2.32,18,122,1.51,1.25,0.21,0.94,4.1,0.76,1.29,630,2
12.88,2.99,2.4,20,104,1.3,1.22,0.24,0.83,5.4,0.74,1.42,530,2
12.81,2.31,2.4,24,98,1.15,1.09,0.27,0.83,5.7,0.66,1.36,560,2
12.7,3.55,2.36,21.5,106,1.7,1.2,0.17,0.84,5,0.78,1.29,600,2
12.51,1.24,2.25,17.5,85,2,0.58,0.6,1.25,5.45,0.75,1.51,650,2
12.6,2.46,2.2,18.5,94,1.62,0.66,0.63,0.94,7.1,0.73,1.58,695,2
12.25,4.72,2.54,21,89,1.38,0.47,0.53,0.8,3.85,0.75,1.27,720,2
12.53,5.51,2.64,25,96,1.79,0.6,0.63,1.1,5,0.82,1.69,515,2
13.49,3.59,2.19,19.5,88,1.62,0.48,0.58,0.88,5.7,0.81,1.82,580,2
12.84,2.96,2.61,24,101,2.32,0.6,0.53,0.81,4.92,0.89,2.15,590,2
12.93,2.81,2.7,21,96,1.54,0.5,0.53,0.75,4.6,0.77,2.31,600,2
13.36,2.56,2.35,20,89,1.4,0.5,0.37,0.64,5.6,0.7,2.47,780,2
13.52,3.17,2.72,23.5,97,1.55,0.52,0.5,0.55,4.35,0.89,2.06,520,2
13.62,4.95,2.35,20,92,2,0.8,0.47,1.02,4.4,0.91,2.05,550,2
12.25,3.88,2.2,18.5,112,1.38,0.78,0.29,1.14,8.21,0.65,2,855,2
13.16,3.57,2.15,21,102,1.5,0.55,0.43,1.3,4,0.6,1.68,830,2
13.88,5.04,2.23,20,80,0.98,0.34,0.4,0.68,4.9,0.58,1.33,415,2
12.87,4.61,2.48,21.5,86,1.7,0.65,0.47,0.86,7.65,0.54,1.86,625,2
13.32,3.24,2.38,21.5,92,1.93,0.76,0.45,1.25,8.42,0.55,1.62,650,2
13.08,3.9,2.36,21.5,113,1.41,1.39,0.34,1.14,9.4,0.57,1.33,550,2
13.5,3.12,2.62,24,123,1.4,1.57,0.22,1.25,8.6,0.59,1.3,500,2
12.79,2.67,2.48,22,112,1.48,1.36,0.24,1.26,10.8,0.48,1.47,480,2
13.11,1.9,2.75,25.5,116,2.2,1.28,0.26,1.56,7.1,0.61,1.33,425,2
13.23,3.3,2.28,18.5,98,1.8,0.83,0.61,1.87,10.52,0.56,1.51,675,2
12.58,1.29,2.1,20,103,1.48,0.58,0.53,1.4,7.6,0.58,1.55,640,2
13.17,5.19,2.32,22,93,1.74,0.63,0.61,1.55,7.9,0.6,1.48,725,2
13.84,4.12,2.38,19.5,89,1.8,0.83,0.48,1.56,9.01,0.57,1.64,480,2
12.45,3.03,2.64,27,97,1.9,0.58,0.63,1.14,7.5,0.67,1.73,880,2
14.34,1.68,2.7,25,98,2.8,1.31,0.53,2.7,13,0.57,1.96,660,2
13.48,1.67,2.64,22.5,89,2.6,1.1,0.52,2.29,11.75,0.57,1.78,620,2
12.36,3.83,2.38,21,88,2.3,0.92,0.5,1.04,7.65,0.56,1.58,520,2
13.69,3.26,2.54,20,107,1.83,0.56,0.5,0.8,5.88,0.96,1.82,680,2
12.85,3.27,2.58,22,106,1.65,0.6,0.6,0.96,5.58,0.87,2.11,570,2
12.96,3.45,2.35,18.5,106,1.39,0.7,0.4,0.94,5.28,0.68,1.75,675,2
13.78,2.76,2.3,22,90,1.35,0.68,0.41,1.03,9.58,0.7,1.68,615,2
13.73,4.36,2.26,22.5,88,1.28,0.47,0.52,1.15,6.62,0.78,1.75,520,2
13.45,3.7,2.6,23,111,1.7,0.92,0.43,1.46,10.68,0.85,1.56,695,2
12.82,3.37,2.3,19.5,88,1.48,0.66,0.4,0.97,10.26,0.72,1.75,685,2
13.58,2.58,2.69,24.5,105,1.55,0.84,0.39,1.54,8.66,0.74,1.8,750,2
13.4,4.6,2.86,25,112,1.98,0.96,0.27,1.11,8.5,0.67,1.92,630,2
12.2,3.03,2.32,19,96,1.25,0.49,0.4,0.73,5.5,0.66,1.83,510,2
12.77,2.39,2.28,19.5,86,1.39,0.51,0.48,0.64,9.899999,0.57,1.63,470,2
14.16,2.51,2.48,20,91,1.68,0.7,0.44,1.24,9.7,0.62,1.71,660,2
13.71,5.65,2.45,20.5,95,1.68,0.61,0.52,1.06,7.7,0.64,1.74,740,2
13.4,3.91,2.48,23,102,1.8,0.75,0.43,1.41,7.3,0.7,1.56,750,2
13.27,4.28,2.26,20,120,1.59,0.69,0.43,1.35,10.2,0.59,1.56,835,2
13.17,2.59,2.37,20,120,1.65,0.68,0.53,1.46,9.3,0.6,1.62,840,2
14.13,4.1,2.74,24.5,96,2.05,0.76,0.56,1.35,9.2,0.61,1.6,560,2
1 178,13,class_0,class_1,class_2
2 14.23,1.71,2.43,15.6,127,2.8,3.06,0.28,2.29,5.64,1.04,3.92,1065,0
3 13.2,1.78,2.14,11.2,100,2.65,2.76,0.26,1.28,4.38,1.05,3.4,1050,0
4 13.16,2.36,2.67,18.6,101,2.8,3.24,0.3,2.81,5.68,1.03,3.17,1185,0
5 14.37,1.95,2.5,16.8,113,3.85,3.49,0.24,2.18,7.8,0.86,3.45,1480,0
6 13.24,2.59,2.87,21,118,2.8,2.69,0.39,1.82,4.32,1.04,2.93,735,0
7 14.2,1.76,2.45,15.2,112,3.27,3.39,0.34,1.97,6.75,1.05,2.85,1450,0
8 14.39,1.87,2.45,14.6,96,2.5,2.52,0.3,1.98,5.25,1.02,3.58,1290,0
9 14.06,2.15,2.61,17.6,121,2.6,2.51,0.31,1.25,5.05,1.06,3.58,1295,0
10 14.83,1.64,2.17,14,97,2.8,2.98,0.29,1.98,5.2,1.08,2.85,1045,0
11 13.86,1.35,2.27,16,98,2.98,3.15,0.22,1.85,7.22,1.01,3.55,1045,0
12 14.1,2.16,2.3,18,105,2.95,3.32,0.22,2.38,5.75,1.25,3.17,1510,0
13 14.12,1.48,2.32,16.8,95,2.2,2.43,0.26,1.57,5,1.17,2.82,1280,0
14 13.75,1.73,2.41,16,89,2.6,2.76,0.29,1.81,5.6,1.15,2.9,1320,0
15 14.75,1.73,2.39,11.4,91,3.1,3.69,0.43,2.81,5.4,1.25,2.73,1150,0
16 14.38,1.87,2.38,12,102,3.3,3.64,0.29,2.96,7.5,1.2,3,1547,0
17 13.63,1.81,2.7,17.2,112,2.85,2.91,0.3,1.46,7.3,1.28,2.88,1310,0
18 14.3,1.92,2.72,20,120,2.8,3.14,0.33,1.97,6.2,1.07,2.65,1280,0
19 13.83,1.57,2.62,20,115,2.95,3.4,0.4,1.72,6.6,1.13,2.57,1130,0
20 14.19,1.59,2.48,16.5,108,3.3,3.93,0.32,1.86,8.7,1.23,2.82,1680,0
21 13.64,3.1,2.56,15.2,116,2.7,3.03,0.17,1.66,5.1,0.96,3.36,845,0
22 14.06,1.63,2.28,16,126,3,3.17,0.24,2.1,5.65,1.09,3.71,780,0
23 12.93,3.8,2.65,18.6,102,2.41,2.41,0.25,1.98,4.5,1.03,3.52,770,0
24 13.71,1.86,2.36,16.6,101,2.61,2.88,0.27,1.69,3.8,1.11,4,1035,0
25 12.85,1.6,2.52,17.8,95,2.48,2.37,0.26,1.46,3.93,1.09,3.63,1015,0
26 13.5,1.81,2.61,20,96,2.53,2.61,0.28,1.66,3.52,1.12,3.82,845,0
27 13.05,2.05,3.22,25,124,2.63,2.68,0.47,1.92,3.58,1.13,3.2,830,0
28 13.39,1.77,2.62,16.1,93,2.85,2.94,0.34,1.45,4.8,0.92,3.22,1195,0
29 13.3,1.72,2.14,17,94,2.4,2.19,0.27,1.35,3.95,1.02,2.77,1285,0
30 13.87,1.9,2.8,19.4,107,2.95,2.97,0.37,1.76,4.5,1.25,3.4,915,0
31 14.02,1.68,2.21,16,96,2.65,2.33,0.26,1.98,4.7,1.04,3.59,1035,0
32 13.73,1.5,2.7,22.5,101,3,3.25,0.29,2.38,5.7,1.19,2.71,1285,0
33 13.58,1.66,2.36,19.1,106,2.86,3.19,0.22,1.95,6.9,1.09,2.88,1515,0
34 13.68,1.83,2.36,17.2,104,2.42,2.69,0.42,1.97,3.84,1.23,2.87,990,0
35 13.76,1.53,2.7,19.5,132,2.95,2.74,0.5,1.35,5.4,1.25,3,1235,0
36 13.51,1.8,2.65,19,110,2.35,2.53,0.29,1.54,4.2,1.1,2.87,1095,0
37 13.48,1.81,2.41,20.5,100,2.7,2.98,0.26,1.86,5.1,1.04,3.47,920,0
38 13.28,1.64,2.84,15.5,110,2.6,2.68,0.34,1.36,4.6,1.09,2.78,880,0
39 13.05,1.65,2.55,18,98,2.45,2.43,0.29,1.44,4.25,1.12,2.51,1105,0
40 13.07,1.5,2.1,15.5,98,2.4,2.64,0.28,1.37,3.7,1.18,2.69,1020,0
41 14.22,3.99,2.51,13.2,128,3,3.04,0.2,2.08,5.1,0.89,3.53,760,0
42 13.56,1.71,2.31,16.2,117,3.15,3.29,0.34,2.34,6.13,0.95,3.38,795,0
43 13.41,3.84,2.12,18.8,90,2.45,2.68,0.27,1.48,4.28,0.91,3,1035,0
44 13.88,1.89,2.59,15,101,3.25,3.56,0.17,1.7,5.43,0.88,3.56,1095,0
45 13.24,3.98,2.29,17.5,103,2.64,2.63,0.32,1.66,4.36,0.82,3,680,0
46 13.05,1.77,2.1,17,107,3,3,0.28,2.03,5.04,0.88,3.35,885,0
47 14.21,4.04,2.44,18.9,111,2.85,2.65,0.3,1.25,5.24,0.87,3.33,1080,0
48 14.38,3.59,2.28,16,102,3.25,3.17,0.27,2.19,4.9,1.04,3.44,1065,0
49 13.9,1.68,2.12,16,101,3.1,3.39,0.21,2.14,6.1,0.91,3.33,985,0
50 14.1,2.02,2.4,18.8,103,2.75,2.92,0.32,2.38,6.2,1.07,2.75,1060,0
51 13.94,1.73,2.27,17.4,108,2.88,3.54,0.32,2.08,8.9,1.12,3.1,1260,0
52 13.05,1.73,2.04,12.4,92,2.72,3.27,0.17,2.91,7.2,1.12,2.91,1150,0
53 13.83,1.65,2.6,17.2,94,2.45,2.99,0.22,2.29,5.6,1.24,3.37,1265,0
54 13.82,1.75,2.42,14,111,3.88,3.74,0.32,1.87,7.05,1.01,3.26,1190,0
55 13.77,1.9,2.68,17.1,115,3,2.79,0.39,1.68,6.3,1.13,2.93,1375,0
56 13.74,1.67,2.25,16.4,118,2.6,2.9,0.21,1.62,5.85,0.92,3.2,1060,0
57 13.56,1.73,2.46,20.5,116,2.96,2.78,0.2,2.45,6.25,0.98,3.03,1120,0
58 14.22,1.7,2.3,16.3,118,3.2,3,0.26,2.03,6.38,0.94,3.31,970,0
59 13.29,1.97,2.68,16.8,102,3,3.23,0.31,1.66,6,1.07,2.84,1270,0
60 13.72,1.43,2.5,16.7,108,3.4,3.67,0.19,2.04,6.8,0.89,2.87,1285,0
61 12.37,0.94,1.36,10.6,88,1.98,0.57,0.28,0.42,1.95,1.05,1.82,520,1
62 12.33,1.1,2.28,16,101,2.05,1.09,0.63,0.41,3.27,1.25,1.67,680,1
63 12.64,1.36,2.02,16.8,100,2.02,1.41,0.53,0.62,5.75,0.98,1.59,450,1
64 13.67,1.25,1.92,18,94,2.1,1.79,0.32,0.73,3.8,1.23,2.46,630,1
65 12.37,1.13,2.16,19,87,3.5,3.1,0.19,1.87,4.45,1.22,2.87,420,1
66 12.17,1.45,2.53,19,104,1.89,1.75,0.45,1.03,2.95,1.45,2.23,355,1
67 12.37,1.21,2.56,18.1,98,2.42,2.65,0.37,2.08,4.6,1.19,2.3,678,1
68 13.11,1.01,1.7,15,78,2.98,3.18,0.26,2.28,5.3,1.12,3.18,502,1
69 12.37,1.17,1.92,19.6,78,2.11,2,0.27,1.04,4.68,1.12,3.48,510,1
70 13.34,0.94,2.36,17,110,2.53,1.3,0.55,0.42,3.17,1.02,1.93,750,1
71 12.21,1.19,1.75,16.8,151,1.85,1.28,0.14,2.5,2.85,1.28,3.07,718,1
72 12.29,1.61,2.21,20.4,103,1.1,1.02,0.37,1.46,3.05,0.906,1.82,870,1
73 13.86,1.51,2.67,25,86,2.95,2.86,0.21,1.87,3.38,1.36,3.16,410,1
74 13.49,1.66,2.24,24,87,1.88,1.84,0.27,1.03,3.74,0.98,2.78,472,1
75 12.99,1.67,2.6,30,139,3.3,2.89,0.21,1.96,3.35,1.31,3.5,985,1
76 11.96,1.09,2.3,21,101,3.38,2.14,0.13,1.65,3.21,0.99,3.13,886,1
77 11.66,1.88,1.92,16,97,1.61,1.57,0.34,1.15,3.8,1.23,2.14,428,1
78 13.03,0.9,1.71,16,86,1.95,2.03,0.24,1.46,4.6,1.19,2.48,392,1
79 11.84,2.89,2.23,18,112,1.72,1.32,0.43,0.95,2.65,0.96,2.52,500,1
80 12.33,0.99,1.95,14.8,136,1.9,1.85,0.35,2.76,3.4,1.06,2.31,750,1
81 12.7,3.87,2.4,23,101,2.83,2.55,0.43,1.95,2.57,1.19,3.13,463,1
82 12,0.92,2,19,86,2.42,2.26,0.3,1.43,2.5,1.38,3.12,278,1
83 12.72,1.81,2.2,18.8,86,2.2,2.53,0.26,1.77,3.9,1.16,3.14,714,1
84 12.08,1.13,2.51,24,78,2,1.58,0.4,1.4,2.2,1.31,2.72,630,1
85 13.05,3.86,2.32,22.5,85,1.65,1.59,0.61,1.62,4.8,0.84,2.01,515,1
86 11.84,0.89,2.58,18,94,2.2,2.21,0.22,2.35,3.05,0.79,3.08,520,1
87 12.67,0.98,2.24,18,99,2.2,1.94,0.3,1.46,2.62,1.23,3.16,450,1
88 12.16,1.61,2.31,22.8,90,1.78,1.69,0.43,1.56,2.45,1.33,2.26,495,1
89 11.65,1.67,2.62,26,88,1.92,1.61,0.4,1.34,2.6,1.36,3.21,562,1
90 11.64,2.06,2.46,21.6,84,1.95,1.69,0.48,1.35,2.8,1,2.75,680,1
91 12.08,1.33,2.3,23.6,70,2.2,1.59,0.42,1.38,1.74,1.07,3.21,625,1
92 12.08,1.83,2.32,18.5,81,1.6,1.5,0.52,1.64,2.4,1.08,2.27,480,1
93 12,1.51,2.42,22,86,1.45,1.25,0.5,1.63,3.6,1.05,2.65,450,1
94 12.69,1.53,2.26,20.7,80,1.38,1.46,0.58,1.62,3.05,0.96,2.06,495,1
95 12.29,2.83,2.22,18,88,2.45,2.25,0.25,1.99,2.15,1.15,3.3,290,1
96 11.62,1.99,2.28,18,98,3.02,2.26,0.17,1.35,3.25,1.16,2.96,345,1
97 12.47,1.52,2.2,19,162,2.5,2.27,0.32,3.28,2.6,1.16,2.63,937,1
98 11.81,2.12,2.74,21.5,134,1.6,0.99,0.14,1.56,2.5,0.95,2.26,625,1
99 12.29,1.41,1.98,16,85,2.55,2.5,0.29,1.77,2.9,1.23,2.74,428,1
100 12.37,1.07,2.1,18.5,88,3.52,3.75,0.24,1.95,4.5,1.04,2.77,660,1
101 12.29,3.17,2.21,18,88,2.85,2.99,0.45,2.81,2.3,1.42,2.83,406,1
102 12.08,2.08,1.7,17.5,97,2.23,2.17,0.26,1.4,3.3,1.27,2.96,710,1
103 12.6,1.34,1.9,18.5,88,1.45,1.36,0.29,1.35,2.45,1.04,2.77,562,1
104 12.34,2.45,2.46,21,98,2.56,2.11,0.34,1.31,2.8,0.8,3.38,438,1
105 11.82,1.72,1.88,19.5,86,2.5,1.64,0.37,1.42,2.06,0.94,2.44,415,1
106 12.51,1.73,1.98,20.5,85,2.2,1.92,0.32,1.48,2.94,1.04,3.57,672,1
107 12.42,2.55,2.27,22,90,1.68,1.84,0.66,1.42,2.7,0.86,3.3,315,1
108 12.25,1.73,2.12,19,80,1.65,2.03,0.37,1.63,3.4,1,3.17,510,1
109 12.72,1.75,2.28,22.5,84,1.38,1.76,0.48,1.63,3.3,0.88,2.42,488,1
110 12.22,1.29,1.94,19,92,2.36,2.04,0.39,2.08,2.7,0.86,3.02,312,1
111 11.61,1.35,2.7,20,94,2.74,2.92,0.29,2.49,2.65,0.96,3.26,680,1
112 11.46,3.74,1.82,19.5,107,3.18,2.58,0.24,3.58,2.9,0.75,2.81,562,1
113 12.52,2.43,2.17,21,88,2.55,2.27,0.26,1.22,2,0.9,2.78,325,1
114 11.76,2.68,2.92,20,103,1.75,2.03,0.6,1.05,3.8,1.23,2.5,607,1
115 11.41,0.74,2.5,21,88,2.48,2.01,0.42,1.44,3.08,1.1,2.31,434,1
116 12.08,1.39,2.5,22.5,84,2.56,2.29,0.43,1.04,2.9,0.93,3.19,385,1
117 11.03,1.51,2.2,21.5,85,2.46,2.17,0.52,2.01,1.9,1.71,2.87,407,1
118 11.82,1.47,1.99,20.8,86,1.98,1.6,0.3,1.53,1.95,0.95,3.33,495,1
119 12.42,1.61,2.19,22.5,108,2,2.09,0.34,1.61,2.06,1.06,2.96,345,1
120 12.77,3.43,1.98,16,80,1.63,1.25,0.43,0.83,3.4,0.7,2.12,372,1
121 12,3.43,2,19,87,2,1.64,0.37,1.87,1.28,0.93,3.05,564,1
122 11.45,2.4,2.42,20,96,2.9,2.79,0.32,1.83,3.25,0.8,3.39,625,1
123 11.56,2.05,3.23,28.5,119,3.18,5.08,0.47,1.87,6,0.93,3.69,465,1
124 12.42,4.43,2.73,26.5,102,2.2,2.13,0.43,1.71,2.08,0.92,3.12,365,1
125 13.05,5.8,2.13,21.5,86,2.62,2.65,0.3,2.01,2.6,0.73,3.1,380,1
126 11.87,4.31,2.39,21,82,2.86,3.03,0.21,2.91,2.8,0.75,3.64,380,1
127 12.07,2.16,2.17,21,85,2.6,2.65,0.37,1.35,2.76,0.86,3.28,378,1
128 12.43,1.53,2.29,21.5,86,2.74,3.15,0.39,1.77,3.94,0.69,2.84,352,1
129 11.79,2.13,2.78,28.5,92,2.13,2.24,0.58,1.76,3,0.97,2.44,466,1
130 12.37,1.63,2.3,24.5,88,2.22,2.45,0.4,1.9,2.12,0.89,2.78,342,1
131 12.04,4.3,2.38,22,80,2.1,1.75,0.42,1.35,2.6,0.79,2.57,580,1
132 12.86,1.35,2.32,18,122,1.51,1.25,0.21,0.94,4.1,0.76,1.29,630,2
133 12.88,2.99,2.4,20,104,1.3,1.22,0.24,0.83,5.4,0.74,1.42,530,2
134 12.81,2.31,2.4,24,98,1.15,1.09,0.27,0.83,5.7,0.66,1.36,560,2
135 12.7,3.55,2.36,21.5,106,1.7,1.2,0.17,0.84,5,0.78,1.29,600,2
136 12.51,1.24,2.25,17.5,85,2,0.58,0.6,1.25,5.45,0.75,1.51,650,2
137 12.6,2.46,2.2,18.5,94,1.62,0.66,0.63,0.94,7.1,0.73,1.58,695,2
138 12.25,4.72,2.54,21,89,1.38,0.47,0.53,0.8,3.85,0.75,1.27,720,2
139 12.53,5.51,2.64,25,96,1.79,0.6,0.63,1.1,5,0.82,1.69,515,2
140 13.49,3.59,2.19,19.5,88,1.62,0.48,0.58,0.88,5.7,0.81,1.82,580,2
141 12.84,2.96,2.61,24,101,2.32,0.6,0.53,0.81,4.92,0.89,2.15,590,2
142 12.93,2.81,2.7,21,96,1.54,0.5,0.53,0.75,4.6,0.77,2.31,600,2
143 13.36,2.56,2.35,20,89,1.4,0.5,0.37,0.64,5.6,0.7,2.47,780,2
144 13.52,3.17,2.72,23.5,97,1.55,0.52,0.5,0.55,4.35,0.89,2.06,520,2
145 13.62,4.95,2.35,20,92,2,0.8,0.47,1.02,4.4,0.91,2.05,550,2
146 12.25,3.88,2.2,18.5,112,1.38,0.78,0.29,1.14,8.21,0.65,2,855,2
147 13.16,3.57,2.15,21,102,1.5,0.55,0.43,1.3,4,0.6,1.68,830,2
148 13.88,5.04,2.23,20,80,0.98,0.34,0.4,0.68,4.9,0.58,1.33,415,2
149 12.87,4.61,2.48,21.5,86,1.7,0.65,0.47,0.86,7.65,0.54,1.86,625,2
150 13.32,3.24,2.38,21.5,92,1.93,0.76,0.45,1.25,8.42,0.55,1.62,650,2
151 13.08,3.9,2.36,21.5,113,1.41,1.39,0.34,1.14,9.4,0.57,1.33,550,2
152 13.5,3.12,2.62,24,123,1.4,1.57,0.22,1.25,8.6,0.59,1.3,500,2
153 12.79,2.67,2.48,22,112,1.48,1.36,0.24,1.26,10.8,0.48,1.47,480,2
154 13.11,1.9,2.75,25.5,116,2.2,1.28,0.26,1.56,7.1,0.61,1.33,425,2
155 13.23,3.3,2.28,18.5,98,1.8,0.83,0.61,1.87,10.52,0.56,1.51,675,2
156 12.58,1.29,2.1,20,103,1.48,0.58,0.53,1.4,7.6,0.58,1.55,640,2
157 13.17,5.19,2.32,22,93,1.74,0.63,0.61,1.55,7.9,0.6,1.48,725,2
158 13.84,4.12,2.38,19.5,89,1.8,0.83,0.48,1.56,9.01,0.57,1.64,480,2
159 12.45,3.03,2.64,27,97,1.9,0.58,0.63,1.14,7.5,0.67,1.73,880,2
160 14.34,1.68,2.7,25,98,2.8,1.31,0.53,2.7,13,0.57,1.96,660,2
161 13.48,1.67,2.64,22.5,89,2.6,1.1,0.52,2.29,11.75,0.57,1.78,620,2
162 12.36,3.83,2.38,21,88,2.3,0.92,0.5,1.04,7.65,0.56,1.58,520,2
163 13.69,3.26,2.54,20,107,1.83,0.56,0.5,0.8,5.88,0.96,1.82,680,2
164 12.85,3.27,2.58,22,106,1.65,0.6,0.6,0.96,5.58,0.87,2.11,570,2
165 12.96,3.45,2.35,18.5,106,1.39,0.7,0.4,0.94,5.28,0.68,1.75,675,2
166 13.78,2.76,2.3,22,90,1.35,0.68,0.41,1.03,9.58,0.7,1.68,615,2
167 13.73,4.36,2.26,22.5,88,1.28,0.47,0.52,1.15,6.62,0.78,1.75,520,2
168 13.45,3.7,2.6,23,111,1.7,0.92,0.43,1.46,10.68,0.85,1.56,695,2
169 12.82,3.37,2.3,19.5,88,1.48,0.66,0.4,0.97,10.26,0.72,1.75,685,2
170 13.58,2.58,2.69,24.5,105,1.55,0.84,0.39,1.54,8.66,0.74,1.8,750,2
171 13.4,4.6,2.86,25,112,1.98,0.96,0.27,1.11,8.5,0.67,1.92,630,2
172 12.2,3.03,2.32,19,96,1.25,0.49,0.4,0.73,5.5,0.66,1.83,510,2
173 12.77,2.39,2.28,19.5,86,1.39,0.51,0.48,0.64,9.899999,0.57,1.63,470,2
174 14.16,2.51,2.48,20,91,1.68,0.7,0.44,1.24,9.7,0.62,1.71,660,2
175 13.71,5.65,2.45,20.5,95,1.68,0.61,0.52,1.06,7.7,0.64,1.74,740,2
176 13.4,3.91,2.48,23,102,1.8,0.75,0.43,1.41,7.3,0.7,1.56,750,2
177 13.27,4.28,2.26,20,120,1.59,0.69,0.43,1.35,10.2,0.59,1.56,835,2
178 13.17,2.59,2.37,20,120,1.65,0.68,0.53,1.46,9.3,0.6,1.62,840,2
179 14.13,4.1,2.74,24.5,96,2.05,0.76,0.56,1.35,9.2,0.61,1.6,560,2
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/breast_cancer.rst
+118 -118
View File
@@ -1,118 +1,118 @@
.. _breast_cancer_dataset:
Breast cancer Wisconsin (diagnostic) dataset
--------------------------------------------
**Data Set Characteristics:**
:Number of Instances: 569
:Number of Attributes: 30 numeric, predictive attributes and the class
:Attribute Information:
- radius (mean of distances from center to points on the perimeter)
- texture (standard deviation of gray-scale values)
- perimeter
- area
- smoothness (local variation in radius lengths)
- compactness (perimeter^2 / area - 1.0)
- concavity (severity of concave portions of the contour)
- concave points (number of concave portions of the contour)
- symmetry
- fractal dimension ("coastline approximation" - 1)
The mean, standard error, and "worst" or largest (mean of the three
worst/largest values) of these features were computed for each image,
resulting in 30 features. For instance, field 0 is Mean Radius, field
10 is Radius SE, field 20 is Worst Radius.
- class:
- WDBC-Malignant
- WDBC-Benign
:Summary Statistics:
===================================== ====== ======
Min Max
===================================== ====== ======
radius (mean): 6.981 28.11
texture (mean): 9.71 39.28
perimeter (mean): 43.79 188.5
area (mean): 143.5 2501.0
smoothness (mean): 0.053 0.163
compactness (mean): 0.019 0.345
concavity (mean): 0.0 0.427
concave points (mean): 0.0 0.201
symmetry (mean): 0.106 0.304
fractal dimension (mean): 0.05 0.097
radius (standard error): 0.112 2.873
texture (standard error): 0.36 4.885
perimeter (standard error): 0.757 21.98
area (standard error): 6.802 542.2
smoothness (standard error): 0.002 0.031
compactness (standard error): 0.002 0.135
concavity (standard error): 0.0 0.396
concave points (standard error): 0.0 0.053
symmetry (standard error): 0.008 0.079
fractal dimension (standard error): 0.001 0.03
radius (worst): 7.93 36.04
texture (worst): 12.02 49.54
perimeter (worst): 50.41 251.2
area (worst): 185.2 4254.0
smoothness (worst): 0.071 0.223
compactness (worst): 0.027 1.058
concavity (worst): 0.0 1.252
concave points (worst): 0.0 0.291
symmetry (worst): 0.156 0.664
fractal dimension (worst): 0.055 0.208
===================================== ====== ======
:Missing Attribute Values: None
:Class Distribution: 212 - Malignant, 357 - Benign
:Creator: Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian
:Donor: Nick Street
:Date: November, 1995
This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.
https://goo.gl/U2Uwz2
Features are computed from a digitized image of a fine needle
aspirate (FNA) of a breast mass. They describe
characteristics of the cell nuclei present in the image.
Separating plane described above was obtained using
Multisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree
Construction Via Linear Programming." Proceedings of the 4th
Midwest Artificial Intelligence and Cognitive Science Society,
pp. 97-101, 1992], a classification method which uses linear
programming to construct a decision tree. Relevant features
were selected using an exhaustive search in the space of 1-4
features and 1-3 separating planes.
The actual linear program used to obtain the separating plane
in the 3-dimensional space is that described in:
[K. P. Bennett and O. L. Mangasarian: "Robust Linear
Programming Discrimination of Two Linearly Inseparable Sets",
Optimization Methods and Software 1, 1992, 23-34].
This database is also available through the UW CS ftp server:
ftp ftp.cs.wisc.edu
cd math-prog/cpo-dataset/machine-learn/WDBC/
.. dropdown:: References
- W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction
for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on
Electronic Imaging: Science and Technology, volume 1905, pages 861-870,
San Jose, CA, 1993.
- O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and
prognosis via linear programming. Operations Research, 43(4), pages 570-577,
July-August 1995.
- W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques
to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994)
163-171.
.. _breast_cancer_dataset:
Breast cancer Wisconsin (diagnostic) dataset
--------------------------------------------
**Data Set Characteristics:**
:Number of Instances: 569
:Number of Attributes: 30 numeric, predictive attributes and the class
:Attribute Information:
- radius (mean of distances from center to points on the perimeter)
- texture (standard deviation of gray-scale values)
- perimeter
- area
- smoothness (local variation in radius lengths)
- compactness (perimeter^2 / area - 1.0)
- concavity (severity of concave portions of the contour)
- concave points (number of concave portions of the contour)
- symmetry
- fractal dimension ("coastline approximation" - 1)
The mean, standard error, and "worst" or largest (mean of the three
worst/largest values) of these features were computed for each image,
resulting in 30 features. For instance, field 0 is Mean Radius, field
10 is Radius SE, field 20 is Worst Radius.
- class:
- WDBC-Malignant
- WDBC-Benign
:Summary Statistics:
===================================== ====== ======
Min Max
===================================== ====== ======
radius (mean): 6.981 28.11
texture (mean): 9.71 39.28
perimeter (mean): 43.79 188.5
area (mean): 143.5 2501.0
smoothness (mean): 0.053 0.163
compactness (mean): 0.019 0.345
concavity (mean): 0.0 0.427
concave points (mean): 0.0 0.201
symmetry (mean): 0.106 0.304
fractal dimension (mean): 0.05 0.097
radius (standard error): 0.112 2.873
texture (standard error): 0.36 4.885
perimeter (standard error): 0.757 21.98
area (standard error): 6.802 542.2
smoothness (standard error): 0.002 0.031
compactness (standard error): 0.002 0.135
concavity (standard error): 0.0 0.396
concave points (standard error): 0.0 0.053
symmetry (standard error): 0.008 0.079
fractal dimension (standard error): 0.001 0.03
radius (worst): 7.93 36.04
texture (worst): 12.02 49.54
perimeter (worst): 50.41 251.2
area (worst): 185.2 4254.0
smoothness (worst): 0.071 0.223
compactness (worst): 0.027 1.058
concavity (worst): 0.0 1.252
concave points (worst): 0.0 0.291
symmetry (worst): 0.156 0.664
fractal dimension (worst): 0.055 0.208
===================================== ====== ======
:Missing Attribute Values: None
:Class Distribution: 212 - Malignant, 357 - Benign
:Creator: Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian
:Donor: Nick Street
:Date: November, 1995
This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.
https://goo.gl/U2Uwz2
Features are computed from a digitized image of a fine needle
aspirate (FNA) of a breast mass. They describe
characteristics of the cell nuclei present in the image.
Separating plane described above was obtained using
Multisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree
Construction Via Linear Programming." Proceedings of the 4th
Midwest Artificial Intelligence and Cognitive Science Society,
pp. 97-101, 1992], a classification method which uses linear
programming to construct a decision tree. Relevant features
were selected using an exhaustive search in the space of 1-4
features and 1-3 separating planes.
The actual linear program used to obtain the separating plane
in the 3-dimensional space is that described in:
[K. P. Bennett and O. L. Mangasarian: "Robust Linear
Programming Discrimination of Two Linearly Inseparable Sets",
Optimization Methods and Software 1, 1992, 23-34].
This database is also available through the UW CS ftp server:
ftp ftp.cs.wisc.edu
cd math-prog/cpo-dataset/machine-learn/WDBC/
.. dropdown:: References
- W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction
for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on
Electronic Imaging: Science and Technology, volume 1905, pages 861-870,
San Jose, CA, 1993.
- O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and
prognosis via linear programming. Operations Research, 43(4), pages 570-577,
July-August 1995.
- W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques
to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994)
163-171.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/california_housing.rst
+46 -46
View File
@@ -1,46 +1,46 @@
.. _california_housing_dataset:
California Housing dataset
--------------------------
**Data Set Characteristics:**
:Number of Instances: 20640
:Number of Attributes: 8 numeric, predictive attributes and the target
:Attribute Information:
- MedInc median income in block group
- HouseAge median house age in block group
- AveRooms average number of rooms per household
- AveBedrms average number of bedrooms per household
- Population block group population
- AveOccup average number of household members
- Latitude block group latitude
- Longitude block group longitude
:Missing Attribute Values: None
This dataset was obtained from the StatLib repository.
https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html
The target variable is the median house value for California districts,
expressed in hundreds of thousands of dollars ($100,000).
This dataset was derived from the 1990 U.S. census, using one row per census
block group. A block group is the smallest geographical unit for which the U.S.
Census Bureau publishes sample data (a block group typically has a population
of 600 to 3,000 people).
A household is a group of people residing within a home. Since the average
number of rooms and bedrooms in this dataset are provided per household, these
columns may take surprisingly large values for block groups with few households
and many empty houses, such as vacation resorts.
It can be downloaded/loaded using the
:func:`sklearn.datasets.fetch_california_housing` function.
.. rubric:: References
- Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,
Statistics and Probability Letters, 33:291-297, 1997.
.. _california_housing_dataset:
California Housing dataset
--------------------------
**Data Set Characteristics:**
:Number of Instances: 20640
:Number of Attributes: 8 numeric, predictive attributes and the target
:Attribute Information:
- MedInc median income in block group
- HouseAge median house age in block group
- AveRooms average number of rooms per household
- AveBedrms average number of bedrooms per household
- Population block group population
- AveOccup average number of household members
- Latitude block group latitude
- Longitude block group longitude
:Missing Attribute Values: None
This dataset was obtained from the StatLib repository.
https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html
The target variable is the median house value for California districts,
expressed in hundreds of thousands of dollars ($100,000).
This dataset was derived from the 1990 U.S. census, using one row per census
block group. A block group is the smallest geographical unit for which the U.S.
Census Bureau publishes sample data (a block group typically has a population
of 600 to 3,000 people).
A household is a group of people residing within a home. Since the average
number of rooms and bedrooms in this dataset are provided per household, these
columns may take surprisingly large values for block groups with few households
and many empty houses, such as vacation resorts.
It can be downloaded/loaded using the
:func:`sklearn.datasets.fetch_california_housing` function.
.. rubric:: References
- Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,
Statistics and Probability Letters, 33:291-297, 1997.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/covtype.rst
+30 -30
View File
@@ -1,30 +1,30 @@
.. _covtype_dataset:
Forest covertypes
-----------------
The samples in this dataset correspond to 30×30m patches of forest in the US,
collected for the task of predicting each patch's cover type,
i.e. the dominant species of tree.
There are seven covertypes, making this a multiclass classification problem.
Each sample has 54 features, described on the
`dataset's homepage <https://archive.ics.uci.edu/ml/datasets/Covertype>`__.
Some of the features are boolean indicators,
while others are discrete or continuous measurements.
**Data Set Characteristics:**
================= ============
Classes 7
Samples total 581012
Dimensionality 54
Features int
================= ============
:func:`sklearn.datasets.fetch_covtype` will load the covertype dataset;
it returns a dictionary-like 'Bunch' object
with the feature matrix in the ``data`` member
and the target values in ``target``. If optional argument 'as_frame' is
set to 'True', it will return ``data`` and ``target`` as pandas
data frame, and there will be an additional member ``frame`` as well.
The dataset will be downloaded from the web if necessary.
.. _covtype_dataset:
Forest covertypes
-----------------
The samples in this dataset correspond to 30×30m patches of forest in the US,
collected for the task of predicting each patch's cover type,
i.e. the dominant species of tree.
There are seven covertypes, making this a multiclass classification problem.
Each sample has 54 features, described on the
`dataset's homepage <https://archive.ics.uci.edu/ml/datasets/Covertype>`__.
Some of the features are boolean indicators,
while others are discrete or continuous measurements.
**Data Set Characteristics:**
================= ============
Classes 7
Samples total 581012
Dimensionality 54
Features int
================= ============
:func:`sklearn.datasets.fetch_covtype` will load the covertype dataset;
it returns a dictionary-like 'Bunch' object
with the feature matrix in the ``data`` member
and the target values in ``target``. If optional argument 'as_frame' is
set to 'True', it will return ``data`` and ``target`` as pandas
data frame, and there will be an additional member ``frame`` as well.
The dataset will be downloaded from the web if necessary.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/diabetes.rst
+38 -38
View File
@@ -1,38 +1,38 @@
.. _diabetes_dataset:
Diabetes dataset
----------------
Ten baseline variables, age, sex, body mass index, average blood
pressure, and six blood serum measurements were obtained for each of n =
442 diabetes patients, as well as the response of interest, a
quantitative measure of disease progression one year after baseline.
**Data Set Characteristics:**
:Number of Instances: 442
:Number of Attributes: First 10 columns are numeric predictive values
:Target: Column 11 is a quantitative measure of disease progression one year after baseline
:Attribute Information:
- age age in years
- sex
- bmi body mass index
- bp average blood pressure
- s1 tc, total serum cholesterol
- s2 ldl, low-density lipoproteins
- s3 hdl, high-density lipoproteins
- s4 tch, total cholesterol / HDL
- s5 ltg, possibly log of serum triglycerides level
- s6 glu, blood sugar level
Note: Each of these 10 feature variables have been mean centered and scaled by the standard deviation times the square root of `n_samples` (i.e. the sum of squares of each column totals 1).
Source URL:
https://www4.stat.ncsu.edu/~boos/var.select/diabetes.html
For more information see:
Bradley Efron, Trevor Hastie, Iain Johnstone and Robert Tibshirani (2004) "Least Angle Regression," Annals of Statistics (with discussion), 407-499.
(https://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf)
.. _diabetes_dataset:
Diabetes dataset
----------------
Ten baseline variables, age, sex, body mass index, average blood
pressure, and six blood serum measurements were obtained for each of n =
442 diabetes patients, as well as the response of interest, a
quantitative measure of disease progression one year after baseline.
**Data Set Characteristics:**
:Number of Instances: 442
:Number of Attributes: First 10 columns are numeric predictive values
:Target: Column 11 is a quantitative measure of disease progression one year after baseline
:Attribute Information:
- age age in years
- sex
- bmi body mass index
- bp average blood pressure
- s1 tc, total serum cholesterol
- s2 ldl, low-density lipoproteins
- s3 hdl, high-density lipoproteins
- s4 tch, total cholesterol / HDL
- s5 ltg, possibly log of serum triglycerides level
- s6 glu, blood sugar level
Note: Each of these 10 feature variables have been mean centered and scaled by the standard deviation times the square root of `n_samples` (i.e. the sum of squares of each column totals 1).
Source URL:
https://www4.stat.ncsu.edu/~boos/var.select/diabetes.html
For more information see:
Bradley Efron, Trevor Hastie, Iain Johnstone and Robert Tibshirani (2004) "Least Angle Regression," Annals of Statistics (with discussion), 407-499.
(https://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf)
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/digits.rst
+46 -46
View File
@@ -1,46 +1,46 @@
.. _digits_dataset:
Optical recognition of handwritten digits dataset
--------------------------------------------------
**Data Set Characteristics:**
:Number of Instances: 1797
:Number of Attributes: 64
:Attribute Information: 8x8 image of integer pixels in the range 0..16.
:Missing Attribute Values: None
:Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)
:Date: July; 1998
This is a copy of the test set of the UCI ML hand-written digits datasets
https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits
The data set contains images of hand-written digits: 10 classes where
each class refers to a digit.
Preprocessing programs made available by NIST were used to extract
normalized bitmaps of handwritten digits from a preprinted form. From a
total of 43 people, 30 contributed to the training set and different 13
to the test set. 32x32 bitmaps are divided into nonoverlapping blocks of
4x4 and the number of on pixels are counted in each block. This generates
an input matrix of 8x8 where each element is an integer in the range
0..16. This reduces dimensionality and gives invariance to small
distortions.
For info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G.
T. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C.
L. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469,
1994.
.. dropdown:: References
- C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their
Applications to Handwritten Digit Recognition, MSc Thesis, Institute of
Graduate Studies in Science and Engineering, Bogazici University.
- E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.
- Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.
Linear dimensionalityreduction using relevance weighted LDA. School of
Electrical and Electronic Engineering Nanyang Technological University.
2005.
- Claudio Gentile. A New Approximate Maximal Margin Classification
Algorithm. NIPS. 2000.
.. _digits_dataset:
Optical recognition of handwritten digits dataset
--------------------------------------------------
**Data Set Characteristics:**
:Number of Instances: 1797
:Number of Attributes: 64
:Attribute Information: 8x8 image of integer pixels in the range 0..16.
:Missing Attribute Values: None
:Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)
:Date: July; 1998
This is a copy of the test set of the UCI ML hand-written digits datasets
https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits
The data set contains images of hand-written digits: 10 classes where
each class refers to a digit.
Preprocessing programs made available by NIST were used to extract
normalized bitmaps of handwritten digits from a preprinted form. From a
total of 43 people, 30 contributed to the training set and different 13
to the test set. 32x32 bitmaps are divided into nonoverlapping blocks of
4x4 and the number of on pixels are counted in each block. This generates
an input matrix of 8x8 where each element is an integer in the range
0..16. This reduces dimensionality and gives invariance to small
distortions.
For info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G.
T. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C.
L. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469,
1994.
.. dropdown:: References
- C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their
Applications to Handwritten Digit Recognition, MSc Thesis, Institute of
Graduate Studies in Science and Engineering, Bogazici University.
- E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.
- Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.
Linear dimensionalityreduction using relevance weighted LDA. School of
Electrical and Electronic Engineering Nanyang Technological University.
2005.
- Claudio Gentile. A New Approximate Maximal Margin Classification
Algorithm. NIPS. 2000.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/iris.rst
+63 -63
View File
@@ -1,63 +1,63 @@
.. _iris_dataset:
Iris plants dataset
--------------------
**Data Set Characteristics:**
:Number of Instances: 150 (50 in each of three classes)
:Number of Attributes: 4 numeric, predictive attributes and the class
:Attribute Information:
- sepal length in cm
- sepal width in cm
- petal length in cm
- petal width in cm
- class:
- Iris-Setosa
- Iris-Versicolour
- Iris-Virginica
:Summary Statistics:
============== ==== ==== ======= ===== ====================
Min Max Mean SD Class Correlation
============== ==== ==== ======= ===== ====================
sepal length: 4.3 7.9 5.84 0.83 0.7826
sepal width: 2.0 4.4 3.05 0.43 -0.4194
petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
============== ==== ==== ======= ===== ====================
:Missing Attribute Values: None
:Class Distribution: 33.3% for each of 3 classes.
:Creator: R.A. Fisher
:Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
:Date: July, 1988
The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken
from Fisher's paper. Note that it's the same as in R, but not as in the UCI
Machine Learning Repository, which has two wrong data points.
This is perhaps the best known database to be found in the
pattern recognition literature. Fisher's paper is a classic in the field and
is referenced frequently to this day. (See Duda & Hart, for example.) The
data set contains 3 classes of 50 instances each, where each class refers to a
type of iris plant. One class is linearly separable from the other 2; the
latter are NOT linearly separable from each other.
.. dropdown:: References
- Fisher, R.A. "The use of multiple measurements in taxonomic problems"
Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
Mathematical Statistics" (John Wiley, NY, 1950).
- Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.
(Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
- Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
Structure and Classification Rule for Recognition in Partially Exposed
Environments". IEEE Transactions on Pattern Analysis and Machine
Intelligence, Vol. PAMI-2, No. 1, 67-71.
- Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions
on Information Theory, May 1972, 431-433.
- See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II
conceptual clustering system finds 3 classes in the data.
- Many, many more ...
.. _iris_dataset:
Iris plants dataset
--------------------
**Data Set Characteristics:**
:Number of Instances: 150 (50 in each of three classes)
:Number of Attributes: 4 numeric, predictive attributes and the class
:Attribute Information:
- sepal length in cm
- sepal width in cm
- petal length in cm
- petal width in cm
- class:
- Iris-Setosa
- Iris-Versicolour
- Iris-Virginica
:Summary Statistics:
============== ==== ==== ======= ===== ====================
Min Max Mean SD Class Correlation
============== ==== ==== ======= ===== ====================
sepal length: 4.3 7.9 5.84 0.83 0.7826
sepal width: 2.0 4.4 3.05 0.43 -0.4194
petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
============== ==== ==== ======= ===== ====================
:Missing Attribute Values: None
:Class Distribution: 33.3% for each of 3 classes.
:Creator: R.A. Fisher
:Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
:Date: July, 1988
The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken
from Fisher's paper. Note that it's the same as in R, but not as in the UCI
Machine Learning Repository, which has two wrong data points.
This is perhaps the best known database to be found in the
pattern recognition literature. Fisher's paper is a classic in the field and
is referenced frequently to this day. (See Duda & Hart, for example.) The
data set contains 3 classes of 50 instances each, where each class refers to a
type of iris plant. One class is linearly separable from the other 2; the
latter are NOT linearly separable from each other.
.. dropdown:: References
- Fisher, R.A. "The use of multiple measurements in taxonomic problems"
Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
Mathematical Statistics" (John Wiley, NY, 1950).
- Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.
(Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
- Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
Structure and Classification Rule for Recognition in Partially Exposed
Environments". IEEE Transactions on Pattern Analysis and Machine
Intelligence, Vol. PAMI-2, No. 1, 67-71.
- Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions
on Information Theory, May 1972, 431-433.
- See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II
conceptual clustering system finds 3 classes in the data.
- Many, many more ...
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/kddcup99.rst
+94 -94
View File
@@ -1,94 +1,94 @@
.. _kddcup99_dataset:
Kddcup 99 dataset
-----------------
The KDD Cup '99 dataset was created by processing the tcpdump portions
of the 1998 DARPA Intrusion Detection System (IDS) Evaluation dataset,
created by MIT Lincoln Lab [2]_. The artificial data (described on the `dataset's
homepage <https://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html>`_) was
generated using a closed network and hand-injected attacks to produce a
large number of different types of attack with normal activity in the
background. As the initial goal was to produce a large training set for
supervised learning algorithms, there is a large proportion (80.1%) of
abnormal data which is unrealistic in real world, and inappropriate for
unsupervised anomaly detection which aims at detecting 'abnormal' data, i.e.:
* qualitatively different from normal data
* in large minority among the observations.
We thus transform the KDD Data set into two different data sets: SA and SF.
* SA is obtained by simply selecting all the normal data, and a small
proportion of abnormal data to gives an anomaly proportion of 1%.
* SF is obtained as in [3]_
by simply picking up the data whose attribute logged_in is positive, thus
focusing on the intrusion attack, which gives a proportion of 0.3% of
attack.
* http and smtp are two subsets of SF corresponding with third feature
equal to 'http' (resp. to 'smtp').
General KDD structure:
================ ==========================================
Samples total 4898431
Dimensionality 41
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
SA structure:
================ ==========================================
Samples total 976158
Dimensionality 41
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
SF structure:
================ ==========================================
Samples total 699691
Dimensionality 4
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
http structure:
================ ==========================================
Samples total 619052
Dimensionality 3
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
smtp structure:
================ ==========================================
Samples total 95373
Dimensionality 3
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
:func:`sklearn.datasets.fetch_kddcup99` will load the kddcup99 dataset; it
returns a dictionary-like object with the feature matrix in the ``data`` member
and the target values in ``target``. The "as_frame" optional argument converts
``data`` into a pandas DataFrame and ``target`` into a pandas Series. The
dataset will be downloaded from the web if necessary.
.. rubric:: References
.. [2] Analysis and Results of the 1999 DARPA Off-Line Intrusion
Detection Evaluation, Richard Lippmann, Joshua W. Haines,
David J. Fried, Jonathan Korba, Kumar Das.
.. [3] K. Yamanishi, J.-I. Takeuchi, G. Williams, and P. Milne. Online
unsupervised outlier detection using finite mixtures with
discounting learning algorithms. In Proceedings of the sixth
ACM SIGKDD international conference on Knowledge discovery
and data mining, pages 320-324. ACM Press, 2000.
.. _kddcup99_dataset:
Kddcup 99 dataset
-----------------
The KDD Cup '99 dataset was created by processing the tcpdump portions
of the 1998 DARPA Intrusion Detection System (IDS) Evaluation dataset,
created by MIT Lincoln Lab [2]_. The artificial data (described on the `dataset's
homepage <https://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html>`_) was
generated using a closed network and hand-injected attacks to produce a
large number of different types of attack with normal activity in the
background. As the initial goal was to produce a large training set for
supervised learning algorithms, there is a large proportion (80.1%) of
abnormal data which is unrealistic in real world, and inappropriate for
unsupervised anomaly detection which aims at detecting 'abnormal' data, i.e.:
* qualitatively different from normal data
* in large minority among the observations.
We thus transform the KDD Data set into two different data sets: SA and SF.
* SA is obtained by simply selecting all the normal data, and a small
proportion of abnormal data to gives an anomaly proportion of 1%.
* SF is obtained as in [3]_
by simply picking up the data whose attribute logged_in is positive, thus
focusing on the intrusion attack, which gives a proportion of 0.3% of
attack.
* http and smtp are two subsets of SF corresponding with third feature
equal to 'http' (resp. to 'smtp').
General KDD structure:
================ ==========================================
Samples total 4898431
Dimensionality 41
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
SA structure:
================ ==========================================
Samples total 976158
Dimensionality 41
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
SF structure:
================ ==========================================
Samples total 699691
Dimensionality 4
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
http structure:
================ ==========================================
Samples total 619052
Dimensionality 3
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
smtp structure:
================ ==========================================
Samples total 95373
Dimensionality 3
Features discrete (int) or continuous (float)
Targets str, 'normal.' or name of the anomaly type
================ ==========================================
:func:`sklearn.datasets.fetch_kddcup99` will load the kddcup99 dataset; it
returns a dictionary-like object with the feature matrix in the ``data`` member
and the target values in ``target``. The "as_frame" optional argument converts
``data`` into a pandas DataFrame and ``target`` into a pandas Series. The
dataset will be downloaded from the web if necessary.
.. rubric:: References
.. [2] Analysis and Results of the 1999 DARPA Off-Line Intrusion
Detection Evaluation, Richard Lippmann, Joshua W. Haines,
David J. Fried, Jonathan Korba, Kumar Das.
.. [3] K. Yamanishi, J.-I. Takeuchi, G. Williams, and P. Milne. Online
unsupervised outlier detection using finite mixtures with
discounting learning algorithms. In Proceedings of the sixth
ACM SIGKDD international conference on Knowledge discovery
and data mining, pages 320-324. ACM Press, 2000.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/lfw.rst
+124 -124
View File
@@ -1,124 +1,124 @@
.. _labeled_faces_in_the_wild_dataset:
The Labeled Faces in the Wild face recognition dataset
------------------------------------------------------
This dataset is a collection of JPEG pictures of famous people collected
over the internet, and the details are available on the Kaggle website:
https://www.kaggle.com/datasets/jessicali9530/lfw-dataset
Each picture is centered on a single face. The typical task is called
Face Verification: given a pair of two pictures, a binary classifier
must predict whether the two images are from the same person.
An alternative task, Face Recognition or Face Identification is:
given the picture of the face of an unknown person, identify the name
of the person by referring to a gallery of previously seen pictures of
identified persons.
Both Face Verification and Face Recognition are tasks that are typically
performed on the output of a model trained to perform Face Detection. The
most popular model for Face Detection is called Viola-Jones and is
implemented in the OpenCV library. The LFW faces were extracted by this
face detector from various online websites.
**Data Set Characteristics:**
================= =======================
Classes 5749
Samples total 13233
Dimensionality 5828
Features real, between 0 and 255
================= =======================
.. dropdown:: Usage
``scikit-learn`` provides two loaders that will automatically download,
cache, parse the metadata files, decode the jpeg and convert the
interesting slices into memmapped numpy arrays. This dataset size is more
than 200 MB. The first load typically takes more than a couple of minutes
to fully decode the relevant part of the JPEG files into numpy arrays. If
the dataset has been loaded once, the following times the loading times
less than 200ms by using a memmapped version memoized on the disk in the
``~/scikit_learn_data/lfw_home/`` folder using ``joblib``.
The first loader is used for the Face Identification task: a multi-class
classification task (hence supervised learning)::
>>> from sklearn.datasets import fetch_lfw_people
>>> lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
>>> for name in lfw_people.target_names:
... print(name)
...
Ariel Sharon
Colin Powell
Donald Rumsfeld
George W Bush
Gerhard Schroeder
Hugo Chavez
Tony Blair
The default slice is a rectangular shape around the face, removing
most of the background::
>>> lfw_people.data.dtype
dtype('float32')
>>> lfw_people.data.shape
(1288, 1850)
>>> lfw_people.images.shape
(1288, 50, 37)
Each of the ``1140`` faces is assigned to a single person id in the ``target``
array::
>>> lfw_people.target.shape
(1288,)
>>> list(lfw_people.target[:10])
[5, 6, 3, 1, 0, 1, 3, 4, 3, 0]
The second loader is typically used for the face verification task: each sample
is a pair of two picture belonging or not to the same person::
>>> from sklearn.datasets import fetch_lfw_pairs
>>> lfw_pairs_train = fetch_lfw_pairs(subset='train')
>>> list(lfw_pairs_train.target_names)
['Different persons', 'Same person']
>>> lfw_pairs_train.pairs.shape
(2200, 2, 62, 47)
>>> lfw_pairs_train.data.shape
(2200, 5828)
>>> lfw_pairs_train.target.shape
(2200,)
Both for the :func:`sklearn.datasets.fetch_lfw_people` and
:func:`sklearn.datasets.fetch_lfw_pairs` function it is
possible to get an additional dimension with the RGB color channels by
passing ``color=True``, in that case the shape will be
``(2200, 2, 62, 47, 3)``.
The :func:`sklearn.datasets.fetch_lfw_pairs` datasets is subdivided into
3 subsets: the development ``train`` set, the development ``test`` set and
an evaluation ``10_folds`` set meant to compute performance metrics using a
10-folds cross validation scheme.
.. rubric:: References
* `Labeled Faces in the Wild: A Database for Studying Face Recognition
in Unconstrained Environments.
<https://people.cs.umass.edu/~elm/papers/lfw.pdf>`_
Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller.
University of Massachusetts, Amherst, Technical Report 07-49, October, 2007.
.. rubric:: Examples
* :ref:`sphx_glr_auto_examples_applications_plot_face_recognition.py`
.. _labeled_faces_in_the_wild_dataset:
The Labeled Faces in the Wild face recognition dataset
------------------------------------------------------
This dataset is a collection of JPEG pictures of famous people collected
over the internet, and the details are available on the Kaggle website:
https://www.kaggle.com/datasets/jessicali9530/lfw-dataset
Each picture is centered on a single face. The typical task is called
Face Verification: given a pair of two pictures, a binary classifier
must predict whether the two images are from the same person.
An alternative task, Face Recognition or Face Identification is:
given the picture of the face of an unknown person, identify the name
of the person by referring to a gallery of previously seen pictures of
identified persons.
Both Face Verification and Face Recognition are tasks that are typically
performed on the output of a model trained to perform Face Detection. The
most popular model for Face Detection is called Viola-Jones and is
implemented in the OpenCV library. The LFW faces were extracted by this
face detector from various online websites.
**Data Set Characteristics:**
================= =======================
Classes 5749
Samples total 13233
Dimensionality 5828
Features real, between 0 and 255
================= =======================
.. dropdown:: Usage
``scikit-learn`` provides two loaders that will automatically download,
cache, parse the metadata files, decode the jpeg and convert the
interesting slices into memmapped numpy arrays. This dataset size is more
than 200 MB. The first load typically takes more than a couple of minutes
to fully decode the relevant part of the JPEG files into numpy arrays. If
the dataset has been loaded once, the following times the loading times
less than 200ms by using a memmapped version memoized on the disk in the
``~/scikit_learn_data/lfw_home/`` folder using ``joblib``.
The first loader is used for the Face Identification task: a multi-class
classification task (hence supervised learning)::
>>> from sklearn.datasets import fetch_lfw_people
>>> lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
>>> for name in lfw_people.target_names:
... print(name)
...
Ariel Sharon
Colin Powell
Donald Rumsfeld
George W Bush
Gerhard Schroeder
Hugo Chavez
Tony Blair
The default slice is a rectangular shape around the face, removing
most of the background::
>>> lfw_people.data.dtype
dtype('float32')
>>> lfw_people.data.shape
(1288, 1850)
>>> lfw_people.images.shape
(1288, 50, 37)
Each of the ``1140`` faces is assigned to a single person id in the ``target``
array::
>>> lfw_people.target.shape
(1288,)
>>> list(lfw_people.target[:10])
[5, 6, 3, 1, 0, 1, 3, 4, 3, 0]
The second loader is typically used for the face verification task: each sample
is a pair of two picture belonging or not to the same person::
>>> from sklearn.datasets import fetch_lfw_pairs
>>> lfw_pairs_train = fetch_lfw_pairs(subset='train')
>>> list(lfw_pairs_train.target_names)
['Different persons', 'Same person']
>>> lfw_pairs_train.pairs.shape
(2200, 2, 62, 47)
>>> lfw_pairs_train.data.shape
(2200, 5828)
>>> lfw_pairs_train.target.shape
(2200,)
Both for the :func:`sklearn.datasets.fetch_lfw_people` and
:func:`sklearn.datasets.fetch_lfw_pairs` function it is
possible to get an additional dimension with the RGB color channels by
passing ``color=True``, in that case the shape will be
``(2200, 2, 62, 47, 3)``.
The :func:`sklearn.datasets.fetch_lfw_pairs` datasets is subdivided into
3 subsets: the development ``train`` set, the development ``test`` set and
an evaluation ``10_folds`` set meant to compute performance metrics using a
10-folds cross validation scheme.
.. rubric:: References
* `Labeled Faces in the Wild: A Database for Studying Face Recognition
in Unconstrained Environments.
<https://people.cs.umass.edu/~elm/papers/lfw.pdf>`_
Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller.
University of Massachusetts, Amherst, Technical Report 07-49, October, 2007.
.. rubric:: Examples
* :ref:`sphx_glr_auto_examples_applications_plot_face_recognition.py`
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/linnerud.rst
+24 -24
View File
@@ -1,24 +1,24 @@
.. _linnerrud_dataset:
Linnerrud dataset
-----------------
**Data Set Characteristics:**
:Number of Instances: 20
:Number of Attributes: 3
:Missing Attribute Values: None
The Linnerud dataset is a multi-output regression dataset. It consists of three
exercise (data) and three physiological (target) variables collected from
twenty middle-aged men in a fitness club:
- *physiological* - CSV containing 20 observations on 3 physiological variables:
Weight, Waist and Pulse.
- *exercise* - CSV containing 20 observations on 3 exercise variables:
Chins, Situps and Jumps.
.. dropdown:: References
* Tenenhaus, M. (1998). La regression PLS: theorie et pratique. Paris:
Editions Technic.
.. _linnerrud_dataset:
Linnerrud dataset
-----------------
**Data Set Characteristics:**
:Number of Instances: 20
:Number of Attributes: 3
:Missing Attribute Values: None
The Linnerud dataset is a multi-output regression dataset. It consists of three
exercise (data) and three physiological (target) variables collected from
twenty middle-aged men in a fitness club:
- *physiological* - CSV containing 20 observations on 3 physiological variables:
Weight, Waist and Pulse.
- *exercise* - CSV containing 20 observations on 3 exercise variables:
Chins, Situps and Jumps.
.. dropdown:: References
* Tenenhaus, M. (1998). La regression PLS: theorie et pratique. Paris:
Editions Technic.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/olivetti_faces.rst
+44 -44
View File
@@ -1,44 +1,44 @@
.. _olivetti_faces_dataset:
The Olivetti faces dataset
--------------------------
`This dataset contains a set of face images`_ taken between April 1992 and
April 1994 at AT&T Laboratories Cambridge. The
:func:`sklearn.datasets.fetch_olivetti_faces` function is the data
fetching / caching function that downloads the data
archive from AT&T.
.. _This dataset contains a set of face images: https://cam-orl.co.uk/facedatabase.html
As described on the original website:
There are ten different images of each of 40 distinct subjects. For some
subjects, the images were taken at different times, varying the lighting,
facial expressions (open / closed eyes, smiling / not smiling) and facial
details (glasses / no glasses). All the images were taken against a dark
homogeneous background with the subjects in an upright, frontal position
(with tolerance for some side movement).
**Data Set Characteristics:**
================= =====================
Classes 40
Samples total 400
Dimensionality 4096
Features real, between 0 and 1
================= =====================
The image is quantized to 256 grey levels and stored as unsigned 8-bit
integers; the loader will convert these to floating point values on the
interval [0, 1], which are easier to work with for many algorithms.
The "target" for this database is an integer from 0 to 39 indicating the
identity of the person pictured; however, with only 10 examples per class, this
relatively small dataset is more interesting from an unsupervised or
semi-supervised perspective.
The original dataset consisted of 92 x 112, while the version available here
consists of 64x64 images.
When using these images, please give credit to AT&T Laboratories Cambridge.
.. _olivetti_faces_dataset:
The Olivetti faces dataset
--------------------------
`This dataset contains a set of face images`_ taken between April 1992 and
April 1994 at AT&T Laboratories Cambridge. The
:func:`sklearn.datasets.fetch_olivetti_faces` function is the data
fetching / caching function that downloads the data
archive from AT&T.
.. _This dataset contains a set of face images: https://cam-orl.co.uk/facedatabase.html
As described on the original website:
There are ten different images of each of 40 distinct subjects. For some
subjects, the images were taken at different times, varying the lighting,
facial expressions (open / closed eyes, smiling / not smiling) and facial
details (glasses / no glasses). All the images were taken against a dark
homogeneous background with the subjects in an upright, frontal position
(with tolerance for some side movement).
**Data Set Characteristics:**
================= =====================
Classes 40
Samples total 400
Dimensionality 4096
Features real, between 0 and 1
================= =====================
The image is quantized to 256 grey levels and stored as unsigned 8-bit
integers; the loader will convert these to floating point values on the
interval [0, 1], which are easier to work with for many algorithms.
The "target" for this database is an integer from 0 to 39 indicating the
identity of the person pictured; however, with only 10 examples per class, this
relatively small dataset is more interesting from an unsupervised or
semi-supervised perspective.
The original dataset consisted of 92 x 112, while the version available here
consists of 64x64 images.
When using these images, please give credit to AT&T Laboratories Cambridge.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/rcv1.rst
+72 -72
View File
@@ -1,72 +1,72 @@
.. _rcv1_dataset:
RCV1 dataset
------------
Reuters Corpus Volume I (RCV1) is an archive of over 800,000 manually
categorized newswire stories made available by Reuters, Ltd. for research
purposes. The dataset is extensively described in [1]_.
**Data Set Characteristics:**
============== =====================
Classes 103
Samples total 804414
Dimensionality 47236
Features real, between 0 and 1
============== =====================
:func:`sklearn.datasets.fetch_rcv1` will load the following
version: RCV1-v2, vectors, full sets, topics multilabels::
>>> from sklearn.datasets import fetch_rcv1
>>> rcv1 = fetch_rcv1()
It returns a dictionary-like object, with the following attributes:
``data``:
The feature matrix is a scipy CSR sparse matrix, with 804414 samples and
47236 features. Non-zero values contains cosine-normalized, log TF-IDF vectors.
A nearly chronological split is proposed in [1]_: The first 23149 samples are
the training set. The last 781265 samples are the testing set. This follows
the official LYRL2004 chronological split. The array has 0.16% of non zero
values::
>>> rcv1.data.shape
(804414, 47236)
``target``:
The target values are stored in a scipy CSR sparse matrix, with 804414 samples
and 103 categories. Each sample has a value of 1 in its categories, and 0 in
others. The array has 3.15% of non zero values::
>>> rcv1.target.shape
(804414, 103)
``sample_id``:
Each sample can be identified by its ID, ranging (with gaps) from 2286
to 810596::
>>> rcv1.sample_id[:3]
array([2286, 2287, 2288], dtype=uint32)
``target_names``:
The target values are the topics of each sample. Each sample belongs to at
least one topic, and to up to 17 topics. There are 103 topics, each
represented by a string. Their corpus frequencies span five orders of
magnitude, from 5 occurrences for 'GMIL', to 381327 for 'CCAT'::
>>> rcv1.target_names[:3].tolist() # doctest: +SKIP
['E11', 'ECAT', 'M11']
The dataset will be downloaded from the `rcv1 homepage`_ if necessary.
The compressed size is about 656 MB.
.. _rcv1 homepage: http://jmlr.csail.mit.edu/papers/volume5/lewis04a/
.. rubric:: References
.. [1] Lewis, D. D., Yang, Y., Rose, T. G., & Li, F. (2004).
RCV1: A new benchmark collection for text categorization research.
The Journal of Machine Learning Research, 5, 361-397.
.. _rcv1_dataset:
RCV1 dataset
------------
Reuters Corpus Volume I (RCV1) is an archive of over 800,000 manually
categorized newswire stories made available by Reuters, Ltd. for research
purposes. The dataset is extensively described in [1]_.
**Data Set Characteristics:**
============== =====================
Classes 103
Samples total 804414
Dimensionality 47236
Features real, between 0 and 1
============== =====================
:func:`sklearn.datasets.fetch_rcv1` will load the following
version: RCV1-v2, vectors, full sets, topics multilabels::
>>> from sklearn.datasets import fetch_rcv1
>>> rcv1 = fetch_rcv1()
It returns a dictionary-like object, with the following attributes:
``data``:
The feature matrix is a scipy CSR sparse matrix, with 804414 samples and
47236 features. Non-zero values contains cosine-normalized, log TF-IDF vectors.
A nearly chronological split is proposed in [1]_: The first 23149 samples are
the training set. The last 781265 samples are the testing set. This follows
the official LYRL2004 chronological split. The array has 0.16% of non zero
values::
>>> rcv1.data.shape
(804414, 47236)
``target``:
The target values are stored in a scipy CSR sparse matrix, with 804414 samples
and 103 categories. Each sample has a value of 1 in its categories, and 0 in
others. The array has 3.15% of non zero values::
>>> rcv1.target.shape
(804414, 103)
``sample_id``:
Each sample can be identified by its ID, ranging (with gaps) from 2286
to 810596::
>>> rcv1.sample_id[:3]
array([2286, 2287, 2288], dtype=uint32)
``target_names``:
The target values are the topics of each sample. Each sample belongs to at
least one topic, and to up to 17 topics. There are 103 topics, each
represented by a string. Their corpus frequencies span five orders of
magnitude, from 5 occurrences for 'GMIL', to 381327 for 'CCAT'::
>>> rcv1.target_names[:3].tolist() # doctest: +SKIP
['E11', 'ECAT', 'M11']
The dataset will be downloaded from the `rcv1 homepage`_ if necessary.
The compressed size is about 656 MB.
.. _rcv1 homepage: http://jmlr.csail.mit.edu/papers/volume5/lewis04a/
.. rubric:: References
.. [1] Lewis, D. D., Yang, Y., Rose, T. G., & Li, F. (2004).
RCV1: A new benchmark collection for text categorization research.
The Journal of Machine Learning Research, 5, 361-397.
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/species_distributions.rst
+40 -40
View File
@@ -1,40 +1,40 @@
.. _species_distribution_dataset:
Species distribution dataset
----------------------------
This dataset represents the geographic distribution of two species in Central and
South America. The two species are:
- `"Bradypus variegatus" <http://www.iucnredlist.org/details/3038/0>`_ ,
the Brown-throated Sloth.
- `"Microryzomys minutus" <http://www.iucnredlist.org/details/13408/0>`_ ,
also known as the Forest Small Rice Rat, a rodent that lives in Peru,
Colombia, Ecuador, Peru, and Venezuela.
The dataset is not a typical dataset since a :class:`~sklearn.datasets.base.Bunch`
containing the attributes `data` and `target` is not returned. Instead, we have
information allowing to create a "density" map of the different species.
The grid for the map can be built using the attributes `x_left_lower_corner`,
`y_left_lower_corner`, `Nx`, `Ny` and `grid_size`, which respectively correspond
to the x and y coordinates of the lower left corner of the grid, the number of
points along the x- and y-axis and the size of the step on the grid.
The density at each location of the grid is contained in the `coverage` attribute.
Finally, the `train` and `test` attributes contain information regarding the location
of a species at a specific location.
The dataset is provided by Phillips et. al. (2006).
.. rubric:: References
* `"Maximum entropy modeling of species geographic distributions"
<http://rob.schapire.net/papers/ecolmod.pdf>`_ S. J. Phillips,
R. P. Anderson, R. E. Schapire - Ecological Modelling, 190:231-259, 2006.
.. rubric:: Examples
* :ref:`sphx_glr_auto_examples_applications_plot_species_distribution_modeling.py`
.. _species_distribution_dataset:
Species distribution dataset
----------------------------
This dataset represents the geographic distribution of two species in Central and
South America. The two species are:
- `"Bradypus variegatus" <http://www.iucnredlist.org/details/3038/0>`_ ,
the Brown-throated Sloth.
- `"Microryzomys minutus" <http://www.iucnredlist.org/details/13408/0>`_ ,
also known as the Forest Small Rice Rat, a rodent that lives in Peru,
Colombia, Ecuador, Peru, and Venezuela.
The dataset is not a typical dataset since a :class:`~sklearn.datasets.base.Bunch`
containing the attributes `data` and `target` is not returned. Instead, we have
information allowing to create a "density" map of the different species.
The grid for the map can be built using the attributes `x_left_lower_corner`,
`y_left_lower_corner`, `Nx`, `Ny` and `grid_size`, which respectively correspond
to the x and y coordinates of the lower left corner of the grid, the number of
points along the x- and y-axis and the size of the step on the grid.
The density at each location of the grid is contained in the `coverage` attribute.
Finally, the `train` and `test` attributes contain information regarding the location
of a species at a specific location.
The dataset is provided by Phillips et. al. (2006).
.. rubric:: References
* `"Maximum entropy modeling of species geographic distributions"
<http://rob.schapire.net/papers/ecolmod.pdf>`_ S. J. Phillips,
R. P. Anderson, R. E. Schapire - Ecological Modelling, 190:231-259, 2006.
.. rubric:: Examples
* :ref:`sphx_glr_auto_examples_applications_plot_species_distribution_modeling.py`
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/twenty_newsgroups.rst
+248 -248
View File
@@ -1,248 +1,248 @@
.. _20newsgroups_dataset:
The 20 newsgroups text dataset
------------------------------
The 20 newsgroups dataset comprises around 18000 newsgroups posts on
20 topics split in two subsets: one for training (or development)
and the other one for testing (or for performance evaluation). The split
between the train and test set is based upon a messages posted before
and after a specific date.
This module contains two loaders. The first one,
:func:`sklearn.datasets.fetch_20newsgroups`,
returns a list of the raw texts that can be fed to text feature
extractors such as :class:`~sklearn.feature_extraction.text.CountVectorizer`
with custom parameters so as to extract feature vectors.
The second one, :func:`sklearn.datasets.fetch_20newsgroups_vectorized`,
returns ready-to-use features, i.e., it is not necessary to use a feature
extractor.
**Data Set Characteristics:**
================= ==========
Classes 20
Samples total 18846
Dimensionality 1
Features text
================= ==========
.. dropdown:: Usage
The :func:`sklearn.datasets.fetch_20newsgroups` function is a data
fetching / caching functions that downloads the data archive from
the original `20 newsgroups website <http://people.csail.mit.edu/jrennie/20Newsgroups/>`__,
extracts the archive contents
in the ``~/scikit_learn_data/20news_home`` folder and calls the
:func:`sklearn.datasets.load_files` on either the training or
testing set folder, or both of them::
>>> from sklearn.datasets import fetch_20newsgroups
>>> newsgroups_train = fetch_20newsgroups(subset='train')
>>> from pprint import pprint
>>> pprint(list(newsgroups_train.target_names))
['alt.atheism',
'comp.graphics',
'comp.os.ms-windows.misc',
'comp.sys.ibm.pc.hardware',
'comp.sys.mac.hardware',
'comp.windows.x',
'misc.forsale',
'rec.autos',
'rec.motorcycles',
'rec.sport.baseball',
'rec.sport.hockey',
'sci.crypt',
'sci.electronics',
'sci.med',
'sci.space',
'soc.religion.christian',
'talk.politics.guns',
'talk.politics.mideast',
'talk.politics.misc',
'talk.religion.misc']
The real data lies in the ``filenames`` and ``target`` attributes. The target
attribute is the integer index of the category::
>>> newsgroups_train.filenames.shape
(11314,)
>>> newsgroups_train.target.shape
(11314,)
>>> newsgroups_train.target[:10]
array([ 7, 4, 4, 1, 14, 16, 13, 3, 2, 4])
It is possible to load only a sub-selection of the categories by passing the
list of the categories to load to the
:func:`sklearn.datasets.fetch_20newsgroups` function::
>>> cats = ['alt.atheism', 'sci.space']
>>> newsgroups_train = fetch_20newsgroups(subset='train', categories=cats)
>>> list(newsgroups_train.target_names)
['alt.atheism', 'sci.space']
>>> newsgroups_train.filenames.shape
(1073,)
>>> newsgroups_train.target.shape
(1073,)
>>> newsgroups_train.target[:10]
array([0, 1, 1, 1, 0, 1, 1, 0, 0, 0])
.. dropdown:: Converting text to vectors
In order to feed predictive or clustering models with the text data,
one first need to turn the text into vectors of numerical values suitable
for statistical analysis. This can be achieved with the utilities of the
``sklearn.feature_extraction.text`` as demonstrated in the following
example that extract `TF-IDF <https://en.wikipedia.org/wiki/Tf-idf>`__ vectors
of unigram tokens from a subset of 20news::
>>> from sklearn.feature_extraction.text import TfidfVectorizer
>>> categories = ['alt.atheism', 'talk.religion.misc',
... 'comp.graphics', 'sci.space']
>>> newsgroups_train = fetch_20newsgroups(subset='train',
... categories=categories)
>>> vectorizer = TfidfVectorizer()
>>> vectors = vectorizer.fit_transform(newsgroups_train.data)
>>> vectors.shape
(2034, 34118)
The extracted TF-IDF vectors are very sparse, with an average of 159 non-zero
components by sample in a more than 30000-dimensional space
(less than .5% non-zero features)::
>>> vectors.nnz / float(vectors.shape[0])
159.01327...
:func:`sklearn.datasets.fetch_20newsgroups_vectorized` is a function which
returns ready-to-use token counts features instead of file names.
.. dropdown:: Filtering text for more realistic training
It is easy for a classifier to overfit on particular things that appear in the
20 Newsgroups data, such as newsgroup headers. Many classifiers achieve very
high F-scores, but their results would not generalize to other documents that
aren't from this window of time.
For example, let's look at the results of a multinomial Naive Bayes classifier,
which is fast to train and achieves a decent F-score::
>>> from sklearn.naive_bayes import MultinomialNB
>>> from sklearn import metrics
>>> newsgroups_test = fetch_20newsgroups(subset='test',
... categories=categories)
>>> vectors_test = vectorizer.transform(newsgroups_test.data)
>>> clf = MultinomialNB(alpha=.01)
>>> clf.fit(vectors, newsgroups_train.target)
MultinomialNB(alpha=0.01, class_prior=None, fit_prior=True)
>>> pred = clf.predict(vectors_test)
>>> metrics.f1_score(newsgroups_test.target, pred, average='macro')
0.88213...
(The example :ref:`sphx_glr_auto_examples_text_plot_document_classification_20newsgroups.py` shuffles
the training and test data, instead of segmenting by time, and in that case
multinomial Naive Bayes gets a much higher F-score of 0.88. Are you suspicious
yet of what's going on inside this classifier?)
Let's take a look at what the most informative features are:
>>> import numpy as np
>>> def show_top10(classifier, vectorizer, categories):
... feature_names = vectorizer.get_feature_names_out()
... for i, category in enumerate(categories):
... top10 = np.argsort(classifier.coef_[i])[-10:]
... print("%s: %s" % (category, " ".join(feature_names[top10])))
...
>>> show_top10(clf, vectorizer, newsgroups_train.target_names)
alt.atheism: edu it and in you that is of to the
comp.graphics: edu in graphics it is for and of to the
sci.space: edu it that is in and space to of the
talk.religion.misc: not it you in is that and to of the
You can now see many things that these features have overfit to:
- Almost every group is distinguished by whether headers such as
``NNTP-Posting-Host:`` and ``Distribution:`` appear more or less often.
- Another significant feature involves whether the sender is affiliated with
a university, as indicated either by their headers or their signature.
- The word "article" is a significant feature, based on how often people quote
previous posts like this: "In article [article ID], [name] <[e-mail address]>
wrote:"
- Other features match the names and e-mail addresses of particular people who
were posting at the time.
With such an abundance of clues that distinguish newsgroups, the classifiers
barely have to identify topics from text at all, and they all perform at the
same high level.
For this reason, the functions that load 20 Newsgroups data provide a
parameter called **remove**, telling it what kinds of information to strip out
of each file. **remove** should be a tuple containing any subset of
``('headers', 'footers', 'quotes')``, telling it to remove headers, signature
blocks, and quotation blocks respectively.
>>> newsgroups_test = fetch_20newsgroups(subset='test',
... remove=('headers', 'footers', 'quotes'),
... categories=categories)
>>> vectors_test = vectorizer.transform(newsgroups_test.data)
>>> pred = clf.predict(vectors_test)
>>> metrics.f1_score(pred, newsgroups_test.target, average='macro')
0.77310...
This classifier lost over a lot of its F-score, just because we removed
metadata that has little to do with topic classification.
It loses even more if we also strip this metadata from the training data:
>>> newsgroups_train = fetch_20newsgroups(subset='train',
... remove=('headers', 'footers', 'quotes'),
... categories=categories)
>>> vectors = vectorizer.fit_transform(newsgroups_train.data)
>>> clf = MultinomialNB(alpha=.01)
>>> clf.fit(vectors, newsgroups_train.target)
MultinomialNB(alpha=0.01, class_prior=None, fit_prior=True)
>>> vectors_test = vectorizer.transform(newsgroups_test.data)
>>> pred = clf.predict(vectors_test)
>>> metrics.f1_score(newsgroups_test.target, pred, average='macro')
0.76995...
Some other classifiers cope better with this harder version of the task. Try the
:ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`
example with and without the `remove` option to compare the results.
.. rubric:: Data Considerations
The Cleveland Indians is a major league baseball team based in Cleveland,
Ohio, USA. In December 2020, it was reported that "After several months of
discussion sparked by the death of George Floyd and a national reckoning over
race and colonialism, the Cleveland Indians have decided to change their
name." Team owner Paul Dolan "did make it clear that the team will not make
its informal nickname -- the Tribe -- its new team name." "It's not going to
be a half-step away from the Indians," Dolan said."We will not have a Native
American-themed name."
https://www.mlb.com/news/cleveland-indians-team-name-change
.. rubric:: Recommendation
- When evaluating text classifiers on the 20 Newsgroups data, you
should strip newsgroup-related metadata. In scikit-learn, you can do this
by setting ``remove=('headers', 'footers', 'quotes')``. The F-score will be
lower because it is more realistic.
- This text dataset contains data which may be inappropriate for certain NLP
applications. An example is listed in the "Data Considerations" section
above. The challenge with using current text datasets in NLP for tasks such
as sentence completion, clustering, and other applications is that text
that is culturally biased and inflammatory will propagate biases. This
should be taken into consideration when using the dataset, reviewing the
output, and the bias should be documented.
.. rubric:: Examples
* :ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`
* :ref:`sphx_glr_auto_examples_text_plot_document_classification_20newsgroups.py`
* :ref:`sphx_glr_auto_examples_text_plot_hashing_vs_dict_vectorizer.py`
* :ref:`sphx_glr_auto_examples_text_plot_document_clustering.py`
.. _20newsgroups_dataset:
The 20 newsgroups text dataset
------------------------------
The 20 newsgroups dataset comprises around 18000 newsgroups posts on
20 topics split in two subsets: one for training (or development)
and the other one for testing (or for performance evaluation). The split
between the train and test set is based upon a messages posted before
and after a specific date.
This module contains two loaders. The first one,
:func:`sklearn.datasets.fetch_20newsgroups`,
returns a list of the raw texts that can be fed to text feature
extractors such as :class:`~sklearn.feature_extraction.text.CountVectorizer`
with custom parameters so as to extract feature vectors.
The second one, :func:`sklearn.datasets.fetch_20newsgroups_vectorized`,
returns ready-to-use features, i.e., it is not necessary to use a feature
extractor.
**Data Set Characteristics:**
================= ==========
Classes 20
Samples total 18846
Dimensionality 1
Features text
================= ==========
.. dropdown:: Usage
The :func:`sklearn.datasets.fetch_20newsgroups` function is a data
fetching / caching functions that downloads the data archive from
the original `20 newsgroups website <http://people.csail.mit.edu/jrennie/20Newsgroups/>`__,
extracts the archive contents
in the ``~/scikit_learn_data/20news_home`` folder and calls the
:func:`sklearn.datasets.load_files` on either the training or
testing set folder, or both of them::
>>> from sklearn.datasets import fetch_20newsgroups
>>> newsgroups_train = fetch_20newsgroups(subset='train')
>>> from pprint import pprint
>>> pprint(list(newsgroups_train.target_names))
['alt.atheism',
'comp.graphics',
'comp.os.ms-windows.misc',
'comp.sys.ibm.pc.hardware',
'comp.sys.mac.hardware',
'comp.windows.x',
'misc.forsale',
'rec.autos',
'rec.motorcycles',
'rec.sport.baseball',
'rec.sport.hockey',
'sci.crypt',
'sci.electronics',
'sci.med',
'sci.space',
'soc.religion.christian',
'talk.politics.guns',
'talk.politics.mideast',
'talk.politics.misc',
'talk.religion.misc']
The real data lies in the ``filenames`` and ``target`` attributes. The target
attribute is the integer index of the category::
>>> newsgroups_train.filenames.shape
(11314,)
>>> newsgroups_train.target.shape
(11314,)
>>> newsgroups_train.target[:10]
array([ 7, 4, 4, 1, 14, 16, 13, 3, 2, 4])
It is possible to load only a sub-selection of the categories by passing the
list of the categories to load to the
:func:`sklearn.datasets.fetch_20newsgroups` function::
>>> cats = ['alt.atheism', 'sci.space']
>>> newsgroups_train = fetch_20newsgroups(subset='train', categories=cats)
>>> list(newsgroups_train.target_names)
['alt.atheism', 'sci.space']
>>> newsgroups_train.filenames.shape
(1073,)
>>> newsgroups_train.target.shape
(1073,)
>>> newsgroups_train.target[:10]
array([0, 1, 1, 1, 0, 1, 1, 0, 0, 0])
.. dropdown:: Converting text to vectors
In order to feed predictive or clustering models with the text data,
one first need to turn the text into vectors of numerical values suitable
for statistical analysis. This can be achieved with the utilities of the
``sklearn.feature_extraction.text`` as demonstrated in the following
example that extract `TF-IDF <https://en.wikipedia.org/wiki/Tf-idf>`__ vectors
of unigram tokens from a subset of 20news::
>>> from sklearn.feature_extraction.text import TfidfVectorizer
>>> categories = ['alt.atheism', 'talk.religion.misc',
... 'comp.graphics', 'sci.space']
>>> newsgroups_train = fetch_20newsgroups(subset='train',
... categories=categories)
>>> vectorizer = TfidfVectorizer()
>>> vectors = vectorizer.fit_transform(newsgroups_train.data)
>>> vectors.shape
(2034, 34118)
The extracted TF-IDF vectors are very sparse, with an average of 159 non-zero
components by sample in a more than 30000-dimensional space
(less than .5% non-zero features)::
>>> vectors.nnz / float(vectors.shape[0])
159.01327...
:func:`sklearn.datasets.fetch_20newsgroups_vectorized` is a function which
returns ready-to-use token counts features instead of file names.
.. dropdown:: Filtering text for more realistic training
It is easy for a classifier to overfit on particular things that appear in the
20 Newsgroups data, such as newsgroup headers. Many classifiers achieve very
high F-scores, but their results would not generalize to other documents that
aren't from this window of time.
For example, let's look at the results of a multinomial Naive Bayes classifier,
which is fast to train and achieves a decent F-score::
>>> from sklearn.naive_bayes import MultinomialNB
>>> from sklearn import metrics
>>> newsgroups_test = fetch_20newsgroups(subset='test',
... categories=categories)
>>> vectors_test = vectorizer.transform(newsgroups_test.data)
>>> clf = MultinomialNB(alpha=.01)
>>> clf.fit(vectors, newsgroups_train.target)
MultinomialNB(alpha=0.01, class_prior=None, fit_prior=True)
>>> pred = clf.predict(vectors_test)
>>> metrics.f1_score(newsgroups_test.target, pred, average='macro')
0.88213...
(The example :ref:`sphx_glr_auto_examples_text_plot_document_classification_20newsgroups.py` shuffles
the training and test data, instead of segmenting by time, and in that case
multinomial Naive Bayes gets a much higher F-score of 0.88. Are you suspicious
yet of what's going on inside this classifier?)
Let's take a look at what the most informative features are:
>>> import numpy as np
>>> def show_top10(classifier, vectorizer, categories):
... feature_names = vectorizer.get_feature_names_out()
... for i, category in enumerate(categories):
... top10 = np.argsort(classifier.coef_[i])[-10:]
... print("%s: %s" % (category, " ".join(feature_names[top10])))
...
>>> show_top10(clf, vectorizer, newsgroups_train.target_names)
alt.atheism: edu it and in you that is of to the
comp.graphics: edu in graphics it is for and of to the
sci.space: edu it that is in and space to of the
talk.religion.misc: not it you in is that and to of the
You can now see many things that these features have overfit to:
- Almost every group is distinguished by whether headers such as
``NNTP-Posting-Host:`` and ``Distribution:`` appear more or less often.
- Another significant feature involves whether the sender is affiliated with
a university, as indicated either by their headers or their signature.
- The word "article" is a significant feature, based on how often people quote
previous posts like this: "In article [article ID], [name] <[e-mail address]>
wrote:"
- Other features match the names and e-mail addresses of particular people who
were posting at the time.
With such an abundance of clues that distinguish newsgroups, the classifiers
barely have to identify topics from text at all, and they all perform at the
same high level.
For this reason, the functions that load 20 Newsgroups data provide a
parameter called **remove**, telling it what kinds of information to strip out
of each file. **remove** should be a tuple containing any subset of
``('headers', 'footers', 'quotes')``, telling it to remove headers, signature
blocks, and quotation blocks respectively.
>>> newsgroups_test = fetch_20newsgroups(subset='test',
... remove=('headers', 'footers', 'quotes'),
... categories=categories)
>>> vectors_test = vectorizer.transform(newsgroups_test.data)
>>> pred = clf.predict(vectors_test)
>>> metrics.f1_score(pred, newsgroups_test.target, average='macro')
0.77310...
This classifier lost over a lot of its F-score, just because we removed
metadata that has little to do with topic classification.
It loses even more if we also strip this metadata from the training data:
>>> newsgroups_train = fetch_20newsgroups(subset='train',
... remove=('headers', 'footers', 'quotes'),
... categories=categories)
>>> vectors = vectorizer.fit_transform(newsgroups_train.data)
>>> clf = MultinomialNB(alpha=.01)
>>> clf.fit(vectors, newsgroups_train.target)
MultinomialNB(alpha=0.01, class_prior=None, fit_prior=True)
>>> vectors_test = vectorizer.transform(newsgroups_test.data)
>>> pred = clf.predict(vectors_test)
>>> metrics.f1_score(newsgroups_test.target, pred, average='macro')
0.76995...
Some other classifiers cope better with this harder version of the task. Try the
:ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`
example with and without the `remove` option to compare the results.
.. rubric:: Data Considerations
The Cleveland Indians is a major league baseball team based in Cleveland,
Ohio, USA. In December 2020, it was reported that "After several months of
discussion sparked by the death of George Floyd and a national reckoning over
race and colonialism, the Cleveland Indians have decided to change their
name." Team owner Paul Dolan "did make it clear that the team will not make
its informal nickname -- the Tribe -- its new team name." "It's not going to
be a half-step away from the Indians," Dolan said."We will not have a Native
American-themed name."
https://www.mlb.com/news/cleveland-indians-team-name-change
.. rubric:: Recommendation
- When evaluating text classifiers on the 20 Newsgroups data, you
should strip newsgroup-related metadata. In scikit-learn, you can do this
by setting ``remove=('headers', 'footers', 'quotes')``. The F-score will be
lower because it is more realistic.
- This text dataset contains data which may be inappropriate for certain NLP
applications. An example is listed in the "Data Considerations" section
above. The challenge with using current text datasets in NLP for tasks such
as sentence completion, clustering, and other applications is that text
that is culturally biased and inflammatory will propagate biases. This
should be taken into consideration when using the dataset, reviewing the
output, and the bias should be documented.
.. rubric:: Examples
* :ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`
* :ref:`sphx_glr_auto_examples_text_plot_document_classification_20newsgroups.py`
* :ref:`sphx_glr_auto_examples_text_plot_hashing_vs_dict_vectorizer.py`
* :ref:`sphx_glr_auto_examples_text_plot_document_clustering.py`
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/descr/wine_data.rst
+94 -94
View File
@@ -1,94 +1,94 @@
.. _wine_dataset:
Wine recognition dataset
------------------------
**Data Set Characteristics:**
:Number of Instances: 178
:Number of Attributes: 13 numeric, predictive attributes and the class
:Attribute Information:
- Alcohol
- Malic acid
- Ash
- Alcalinity of ash
- Magnesium
- Total phenols
- Flavanoids
- Nonflavanoid phenols
- Proanthocyanins
- Color intensity
- Hue
- OD280/OD315 of diluted wines
- Proline
- class:
- class_0
- class_1
- class_2
:Summary Statistics:
============================= ==== ===== ======= =====
Min Max Mean SD
============================= ==== ===== ======= =====
Alcohol: 11.0 14.8 13.0 0.8
Malic Acid: 0.74 5.80 2.34 1.12
Ash: 1.36 3.23 2.36 0.27
Alcalinity of Ash: 10.6 30.0 19.5 3.3
Magnesium: 70.0 162.0 99.7 14.3
Total Phenols: 0.98 3.88 2.29 0.63
Flavanoids: 0.34 5.08 2.03 1.00
Nonflavanoid Phenols: 0.13 0.66 0.36 0.12
Proanthocyanins: 0.41 3.58 1.59 0.57
Colour Intensity: 1.3 13.0 5.1 2.3
Hue: 0.48 1.71 0.96 0.23
OD280/OD315 of diluted wines: 1.27 4.00 2.61 0.71
Proline: 278 1680 746 315
============================= ==== ===== ======= =====
:Missing Attribute Values: None
:Class Distribution: class_0 (59), class_1 (71), class_2 (48)
:Creator: R.A. Fisher
:Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
:Date: July, 1988
This is a copy of UCI ML Wine recognition datasets.
https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data
The data is the results of a chemical analysis of wines grown in the same
region in Italy by three different cultivators. There are thirteen different
measurements taken for different constituents found in the three types of
wine.
Original Owners:
Forina, M. et al, PARVUS -
An Extendible Package for Data Exploration, Classification and Correlation.
Institute of Pharmaceutical and Food Analysis and Technologies,
Via Brigata Salerno, 16147 Genoa, Italy.
Citation:
Lichman, M. (2013). UCI Machine Learning Repository
[https://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
School of Information and Computer Science.
.. dropdown:: References
(1) S. Aeberhard, D. Coomans and O. de Vel,
Comparison of Classifiers in High Dimensional Settings,
Tech. Rep. no. 92-02, (1992), Dept. of Computer Science and Dept. of
Mathematics and Statistics, James Cook University of North Queensland.
(Also submitted to Technometrics).
The data was used with many others for comparing various
classifiers. The classes are separable, though only RDA
has achieved 100% correct classification.
(RDA : 100%, QDA 99.4%, LDA 98.9%, 1NN 96.1% (z-transformed data))
(All results using the leave-one-out technique)
(2) S. Aeberhard, D. Coomans and O. de Vel,
"THE CLASSIFICATION PERFORMANCE OF RDA"
Tech. Rep. no. 92-01, (1992), Dept. of Computer Science and Dept. of
Mathematics and Statistics, James Cook University of North Queensland.
(Also submitted to Journal of Chemometrics).
.. _wine_dataset:
Wine recognition dataset
------------------------
**Data Set Characteristics:**
:Number of Instances: 178
:Number of Attributes: 13 numeric, predictive attributes and the class
:Attribute Information:
- Alcohol
- Malic acid
- Ash
- Alcalinity of ash
- Magnesium
- Total phenols
- Flavanoids
- Nonflavanoid phenols
- Proanthocyanins
- Color intensity
- Hue
- OD280/OD315 of diluted wines
- Proline
- class:
- class_0
- class_1
- class_2
:Summary Statistics:
============================= ==== ===== ======= =====
Min Max Mean SD
============================= ==== ===== ======= =====
Alcohol: 11.0 14.8 13.0 0.8
Malic Acid: 0.74 5.80 2.34 1.12
Ash: 1.36 3.23 2.36 0.27
Alcalinity of Ash: 10.6 30.0 19.5 3.3
Magnesium: 70.0 162.0 99.7 14.3
Total Phenols: 0.98 3.88 2.29 0.63
Flavanoids: 0.34 5.08 2.03 1.00
Nonflavanoid Phenols: 0.13 0.66 0.36 0.12
Proanthocyanins: 0.41 3.58 1.59 0.57
Colour Intensity: 1.3 13.0 5.1 2.3
Hue: 0.48 1.71 0.96 0.23
OD280/OD315 of diluted wines: 1.27 4.00 2.61 0.71
Proline: 278 1680 746 315
============================= ==== ===== ======= =====
:Missing Attribute Values: None
:Class Distribution: class_0 (59), class_1 (71), class_2 (48)
:Creator: R.A. Fisher
:Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
:Date: July, 1988
This is a copy of UCI ML Wine recognition datasets.
https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data
The data is the results of a chemical analysis of wines grown in the same
region in Italy by three different cultivators. There are thirteen different
measurements taken for different constituents found in the three types of
wine.
Original Owners:
Forina, M. et al, PARVUS -
An Extendible Package for Data Exploration, Classification and Correlation.
Institute of Pharmaceutical and Food Analysis and Technologies,
Via Brigata Salerno, 16147 Genoa, Italy.
Citation:
Lichman, M. (2013). UCI Machine Learning Repository
[https://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
School of Information and Computer Science.
.. dropdown:: References
(1) S. Aeberhard, D. Coomans and O. de Vel,
Comparison of Classifiers in High Dimensional Settings,
Tech. Rep. no. 92-02, (1992), Dept. of Computer Science and Dept. of
Mathematics and Statistics, James Cook University of North Queensland.
(Also submitted to Technometrics).
The data was used with many others for comparing various
classifiers. The classes are separable, though only RDA
has achieved 100% correct classification.
(RDA : 100%, QDA 99.4%, LDA 98.9%, 1NN 96.1% (z-transformed data))
(All results using the leave-one-out technique)
(2) S. Aeberhard, D. Coomans and O. de Vel,
"THE CLASSIFICATION PERFORMANCE OF RDA"
Tech. Rep. no. 92-01, (1992), Dept. of Computer Science and Dept. of
Mathematics and Statistics, James Cook University of North Queensland.
(Also submitted to Journal of Chemometrics).
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/images/README.txt
+18 -18
View File
@@ -1,18 +1,18 @@
Image: china.jpg
Released under a creative commons license. [1]
Attribution: Some rights reserved by danielbuechele [2]
Retrieved 21st August, 2011 from [3] by Robert Layton
[1] https://creativecommons.org/licenses/by/2.0/
[2] https://www.flickr.com/photos/danielbuechele/
[3] https://www.flickr.com/photos/danielbuechele/6061409035/sizes/z/in/photostream/
Image: flower.jpg
Released under a creative commons license. [1]
Attribution: Some rights reserved by danielbuechele [2]
Retrieved 21st August, 2011 from [3] by Robert Layton
[1] https://creativecommons.org/licenses/by/2.0/
[2] https://www.flickr.com/photos/vultilion/
[3] https://www.flickr.com/photos/vultilion/6056698931/sizes/z/in/photostream/
Image: china.jpg
Released under a creative commons license. [1]
Attribution: Some rights reserved by danielbuechele [2]
Retrieved 21st August, 2011 from [3] by Robert Layton
[1] https://creativecommons.org/licenses/by/2.0/
[2] https://www.flickr.com/photos/danielbuechele/
[3] https://www.flickr.com/photos/danielbuechele/6061409035/sizes/z/in/photostream/
Image: flower.jpg
Released under a creative commons license. [1]
Attribution: Some rights reserved by danielbuechele [2]
Retrieved 21st August, 2011 from [3] by Robert Layton
[1] https://creativecommons.org/licenses/by/2.0/
[2] https://www.flickr.com/photos/vultilion/
[3] https://www.flickr.com/photos/vultilion/6056698931/sizes/z/in/photostream/
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/meson.build
+7 -7
View File
@@ -1,7 +1,7 @@
py.extension_module(
'_svmlight_format_fast',
cython_gen.process('_svmlight_format_fast.pyx'),
dependencies: [np_dep],
subdir: 'sklearn/datasets',
install: true
)
py.extension_module(
'_svmlight_format_fast',
cython_gen.process('_svmlight_format_fast.pyx'),
dependencies: [np_dep],
subdir: 'sklearn/datasets',
install: true
)
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/tests/data/svmlight_classification.txt
+9 -9
View File
@@ -1,9 +1,9 @@
# comment
# note: the next line contains a tab
1.0 3:2.5 11:-5.2 16:1.5 # and an inline comment
2.0 6:1.0 13:-3
# another comment
3.0 21:27
4.0 2:1.234567890123456e10 # double precision value
1.0 # empty line, all zeros
2.0 3:0 # explicit zeros
# comment
# note: the next line contains a tab
1.0 3:2.5 11:-5.2 16:1.5 # and an inline comment
2.0 6:1.0 13:-3
# another comment
3.0 21:27
4.0 2:1.234567890123456e10 # double precision value
1.0 # empty line, all zeros
2.0 3:0 # explicit zeros
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/tests/data/svmlight_invalid.txt
+3 -3
View File
@@ -1,3 +1,3 @@
python 2:2.5 10:-5.2 15:1.5
2.0 5:1.0 12:-3
3.0 20:27
python 2:2.5 10:-5.2 15:1.5
2.0 5:1.0 12:-3
3.0 20:27
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/tests/data/svmlight_invalid_order.txt
+1 -1
View File
@@ -1 +1 @@
-1 5:2.5 2:-5.2 15:1.5
-1 5:2.5 2:-5.2 15:1.5
CameraAI~/Tools~/CWCameraWorker/_internal/sklearn/datasets/tests/data/svmlight_multilabel.txt
+5 -5
View File
@@ -1,5 +1,5 @@
# multilabel dataset in SVMlight format
1,0 2:2.5 10:-5.2 15:1.5
2 5:1.0 12:-3
2:3.5 11:26
1,2 20:27
# multilabel dataset in SVMlight format
1,0 2:2.5 10:-5.2 15:1.5
2 5:1.0 12:-3
2:3.5 11:26
1,2 20:27