/usr/lib/python3/dist-packages/patsy/test_state.py is in python3-patsy 0.4.1+git34-ga5b54c2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | # This file is part of Patsy
# Copyright (C) 2012-2013 Nathaniel Smith <njs@pobox.com>
# See file LICENSE.txt for license information.
from __future__ import print_function
import numpy as np
from patsy.state import Center, Standardize, center
from patsy.util import atleast_2d_column_default
def check_stateful(cls, accepts_multicolumn, input, output, *args, **kwargs):
input = np.asarray(input)
output = np.asarray(output)
test_cases = [
# List input, one chunk
([input], output),
# Scalar input, many chunks
(input, output),
# List input, many chunks:
([[n] for n in input], output),
# 0-d array input, many chunks:
([np.array(n) for n in input], output),
# 1-d array input, one chunk:
([np.array(input)], output),
# 1-d array input, many chunks:
([np.array([n]) for n in input], output),
# 2-d but 1 column input, one chunk:
([np.array(input)[:, None]], atleast_2d_column_default(output)),
# 2-d but 1 column input, many chunks:
([np.array([[n]]) for n in input], atleast_2d_column_default(output)),
]
if accepts_multicolumn:
# 2-d array input, one chunk:
test_cases += [
([np.column_stack((input, input[::-1]))],
np.column_stack((output, output[::-1]))),
# 2-d array input, many chunks:
([np.array([[input[i], input[-i-1]]]) for i in range(len(input))],
np.column_stack((output, output[::-1]))),
]
from patsy.util import have_pandas
if have_pandas:
import pandas
pandas_type = (pandas.Series, pandas.DataFrame)
pandas_index = np.linspace(0, 1, num=len(input))
# 1d and 2d here refer to the dimensionality of the input
if output.ndim == 1:
output_1d = pandas.Series(output, index=pandas_index)
else:
output_1d = pandas.DataFrame(output, index=pandas_index)
test_cases += [
# Series input, one chunk
([pandas.Series(input, index=pandas_index)], output_1d),
# Series input, many chunks
([pandas.Series([x], index=[idx])
for (x, idx) in zip(input, pandas_index)],
output_1d),
]
if accepts_multicolumn:
input_2d_2col = np.column_stack((input, input[::-1]))
output_2d_2col = np.column_stack((output, output[::-1]))
output_2col_dataframe = pandas.DataFrame(output_2d_2col,
index=pandas_index)
test_cases += [
# DataFrame input, one chunk
([pandas.DataFrame(input_2d_2col, index=pandas_index)],
output_2col_dataframe),
# DataFrame input, many chunks
([pandas.DataFrame([input_2d_2col[i, :]],
index=[pandas_index[i]])
for i in range(len(input))],
output_2col_dataframe),
]
for input_obj, output_obj in test_cases:
print(input_obj)
t = cls()
for input_chunk in input_obj:
t.memorize_chunk(input_chunk, *args, **kwargs)
t.memorize_finish()
all_outputs = []
for input_chunk in input_obj:
output_chunk = t.transform(input_chunk, *args, **kwargs)
if input.ndim == output.ndim:
assert output_chunk.ndim == np.asarray(input_chunk).ndim
all_outputs.append(output_chunk)
if have_pandas and isinstance(all_outputs[0], pandas_type):
all_output1 = pandas.concat(all_outputs)
assert np.array_equal(all_output1.index, pandas_index)
elif all_outputs[0].ndim == 0:
all_output1 = np.array(all_outputs)
elif all_outputs[0].ndim == 1:
all_output1 = np.concatenate(all_outputs)
else:
all_output1 = np.row_stack(all_outputs)
assert all_output1.shape[0] == len(input)
# output_obj_reshaped = np.asarray(output_obj).reshape(all_output1.shape)
# assert np.allclose(all_output1, output_obj_reshaped)
assert np.allclose(all_output1, output_obj)
if np.asarray(input_obj[0]).ndim == 0:
all_input = np.array(input_obj)
elif have_pandas and isinstance(input_obj[0], pandas_type):
# handles both Series and DataFrames
all_input = pandas.concat(input_obj)
elif np.asarray(input_obj[0]).ndim == 1:
# Don't use row_stack, because that would turn this into a 1xn
# matrix:
all_input = np.concatenate(input_obj)
else:
all_input = np.row_stack(input_obj)
all_output2 = t.transform(all_input, *args, **kwargs)
if have_pandas and isinstance(input_obj[0], pandas_type):
assert np.array_equal(all_output2.index, pandas_index)
if input.ndim == output.ndim:
assert all_output2.ndim == all_input.ndim
assert np.allclose(all_output2, output_obj)
def test_Center():
check_stateful(Center, True, [1, 2, 3], [-1, 0, 1])
check_stateful(Center, True, [1, 2, 1, 2], [-0.5, 0.5, -0.5, 0.5])
check_stateful(Center, True,
[1.3, -10.1, 7.0, 12.0],
[-1.25, -12.65, 4.45, 9.45])
def test_stateful_transform_wrapper():
assert np.allclose(center([1, 2, 3]), [-1, 0, 1])
assert np.allclose(center([1, 2, 1, 2]), [-0.5, 0.5, -0.5, 0.5])
assert center([1.0, 2.0, 3.0]).dtype == np.dtype(float)
assert (center(np.array([1.0, 2.0, 3.0], dtype=np.float32)).dtype
== np.dtype(np.float32))
assert center([1, 2, 3]).dtype == np.dtype(float)
from patsy.util import have_pandas
if have_pandas:
import pandas
s = pandas.Series([1, 2, 3], index=["a", "b", "c"])
df = pandas.DataFrame([[1, 2], [2, 4], [3, 6]],
columns=["x1", "x2"],
index=[10, 20, 30])
s_c = center(s)
assert isinstance(s_c, pandas.Series)
assert np.array_equal(s_c.index, ["a", "b", "c"])
assert np.allclose(s_c, [-1, 0, 1])
df_c = center(df)
assert isinstance(df_c, pandas.DataFrame)
assert np.array_equal(df_c.index, [10, 20, 30])
assert np.array_equal(df_c.columns, ["x1", "x2"])
assert np.allclose(df_c, [[-1, -2], [0, 0], [1, 2]])
def test_Standardize():
check_stateful(Standardize, True, [1, -1], [1, -1])
check_stateful(Standardize, True, [12, 10], [1, -1])
check_stateful(Standardize, True,
[12, 11, 10],
[np.sqrt(3./2), 0, -np.sqrt(3./2)])
check_stateful(Standardize, True,
[12.0, 11.0, 10.0],
[np.sqrt(3./2), 0, -np.sqrt(3./2)])
# XX: see the comment in Standardize.transform about why this doesn't
# work:
# check_stateful(Standardize,
# [12.0+0j, 11.0+0j, 10.0],
# [np.sqrt(3./2)+0j, 0, -np.sqrt(3./2)])
r20 = list(range(20))
check_stateful(Standardize, True, [1, -1], [np.sqrt(2)/2, -np.sqrt(2)/2],
ddof=1)
check_stateful(Standardize, True,
r20,
list((np.arange(20) - 9.5) / 5.7662812973353983),
ddof=0)
check_stateful(Standardize, True,
r20,
list((np.arange(20) - 9.5) / 5.9160797830996161),
ddof=1)
check_stateful(Standardize, True,
r20,
list((np.arange(20) - 9.5)),
rescale=False, ddof=1)
check_stateful(Standardize, True,
r20,
list(np.arange(20) / 5.9160797830996161),
center=False, ddof=1)
check_stateful(Standardize, True,
r20,
r20,
center=False, rescale=False, ddof=1)
|