/usr/share/pyshared/patsy/test_highlevel.py is in python-patsy 0.2.1-3.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 | # This file is part of Patsy
# Copyright (C) 2012-2013 Nathaniel Smith <njs@pobox.com>
# See file COPYING for license information.
# Exhaustive end-to-end tests of the top-level API.
import sys
import __future__
import numpy as np
from nose.tools import assert_raises
from patsy import PatsyError
from patsy.design_info import DesignMatrix
from patsy.eval import EvalEnvironment
from patsy.desc import ModelDesc, Term, INTERCEPT
from patsy.categorical import C
from patsy.contrasts import Helmert
from patsy.user_util import balanced, LookupFactor
from patsy.build import (design_matrix_builders,
build_design_matrices,
DesignMatrixBuilder)
from patsy.highlevel import *
from patsy.util import have_pandas
from patsy.origin import Origin
if have_pandas:
import pandas
def check_result(expect_builders, lhs, rhs, data,
expected_rhs_values, expected_rhs_names,
expected_lhs_values, expected_lhs_names): # pragma: no cover
assert np.allclose(rhs, expected_rhs_values)
assert rhs.design_info.column_names == expected_rhs_names
if lhs is not None:
assert np.allclose(lhs, expected_lhs_values)
assert lhs.design_info.column_names == expected_lhs_names
else:
assert expected_lhs_values is None
assert expected_lhs_names is None
if expect_builders:
if lhs is None:
new_rhs, = build_design_matrices([rhs.design_info.builder], data)
else:
new_lhs, new_rhs = build_design_matrices([lhs.design_info.builder,
rhs.design_info.builder],
data)
assert np.allclose(new_lhs, lhs)
assert new_lhs.design_info.column_names == expected_lhs_names
assert np.allclose(new_rhs, rhs)
assert new_rhs.design_info.column_names == expected_rhs_names
else:
assert rhs.design_info.builder is None
assert lhs is None or lhs.design_info.builder is None
def dmatrix_pandas(formula_like, data={}, depth=0, return_type="matrix"):
return_type = "dataframe"
if isinstance(depth, int):
depth += 1
return dmatrix(formula_like, data, depth, return_type=return_type)
def dmatrices_pandas(formula_like, data={}, depth=0, return_type="matrix"):
return_type = "dataframe"
if isinstance(depth, int):
depth += 1
return dmatrices(formula_like, data, depth, return_type=return_type)
def t(formula_like, data, depth,
expect_builders,
expected_rhs_values, expected_rhs_names,
expected_lhs_values=None, expected_lhs_names=None): # pragma: no cover
if isinstance(depth, int):
depth += 1
def data_iter_maker():
return iter([data])
if (isinstance(formula_like, (basestring, ModelDesc, DesignMatrixBuilder))
or (isinstance(formula_like, tuple)
and isinstance(formula_like[0], DesignMatrixBuilder))
or hasattr(formula_like, "__patsy_get_model_desc__")):
if expected_lhs_values is None:
builder = incr_dbuilder(formula_like, data_iter_maker, depth)
lhs = None
(rhs,) = build_design_matrices([builder], data)
else:
builders = incr_dbuilders(formula_like, data_iter_maker, depth)
lhs, rhs = build_design_matrices(builders, data)
check_result(expect_builders, lhs, rhs, data,
expected_rhs_values, expected_rhs_names,
expected_lhs_values, expected_lhs_names)
else:
assert_raises(PatsyError, incr_dbuilders,
formula_like, data_iter_maker)
assert_raises(PatsyError, incr_dbuilder,
formula_like, data_iter_maker)
one_mat_fs = [dmatrix]
two_mat_fs = [dmatrices]
if have_pandas:
one_mat_fs.append(dmatrix_pandas)
two_mat_fs.append(dmatrices_pandas)
if expected_lhs_values is None:
for f in one_mat_fs:
rhs = f(formula_like, data, depth)
check_result(expect_builders, None, rhs, data,
expected_rhs_values, expected_rhs_names,
expected_lhs_values, expected_lhs_names)
# We inline assert_raises here to avoid complications with the
# depth argument.
for f in two_mat_fs:
try:
f(formula_like, data, depth)
except PatsyError:
pass
else:
raise AssertionError
else:
for f in one_mat_fs:
try:
f(formula_like, data, depth)
except PatsyError:
pass
else:
raise AssertionError
for f in two_mat_fs:
(lhs, rhs) = f(formula_like, data, depth)
check_result(expect_builders, lhs, rhs, data,
expected_rhs_values, expected_rhs_names,
expected_lhs_values, expected_lhs_names)
def t_invalid(formula_like, data, depth, exc=PatsyError): # pragma: no cover
if isinstance(depth, int):
depth += 1
fs = [dmatrix, dmatrices]
if have_pandas:
fs += [dmatrix_pandas, dmatrices_pandas]
for f in fs:
try:
f(formula_like, data, depth)
except exc:
pass
else:
raise AssertionError
# Exercise all the different calling conventions for the high-level API
def test_formula_likes():
# Plain array-like, rhs only
t([[1, 2, 3], [4, 5, 6]], {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
t((None, [[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
t(np.asarray([[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
t((None, np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
dm = DesignMatrix([[1, 2, 3], [4, 5, 6]], default_column_prefix="foo")
t(dm, {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"])
t((None, dm), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"])
# Plain array-likes, lhs and rhs
t(([1, 2], [[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
t(([[1], [2]], [[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
t((np.asarray([1, 2]), np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
t((np.asarray([[1], [2]]), np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
x_dm = DesignMatrix([[1, 2, 3], [4, 5, 6]], default_column_prefix="foo")
y_dm = DesignMatrix([1, 2], default_column_prefix="bar")
t((y_dm, x_dm), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"],
[[1], [2]], ["bar0"])
# number of rows must match
t_invalid(([1, 2, 3], [[1, 2, 3], [4, 5, 6]]), {}, 0)
# tuples must have the right size
t_invalid(([[1, 2, 3]],), {}, 0)
t_invalid(([[1, 2, 3]], [[1, 2, 3]], [[1, 2, 3]]), {}, 0)
# plain Series and DataFrames
if have_pandas:
# Names are extracted
t(pandas.DataFrame({"x": [1, 2, 3]}), {}, 0,
False,
[[1], [2], [3]], ["x"])
t(pandas.Series([1, 2, 3], name="asdf"), {}, 0,
False,
[[1], [2], [3]], ["asdf"])
t((pandas.DataFrame({"y": [4, 5, 6]}),
pandas.DataFrame({"x": [1, 2, 3]})), {}, 0,
False,
[[1], [2], [3]], ["x"],
[[4], [5], [6]], ["y"])
t((pandas.Series([4, 5, 6], name="y"),
pandas.Series([1, 2, 3], name="x")), {}, 0,
False,
[[1], [2], [3]], ["x"],
[[4], [5], [6]], ["y"])
# Or invented
t((pandas.DataFrame([[4, 5, 6]]),
pandas.DataFrame([[1, 2, 3]], columns=[7, 8, 9])), {}, 0,
False,
[[1, 2, 3]], ["x7", "x8", "x9"],
[[4, 5, 6]], ["y0", "y1", "y2"])
t(pandas.Series([1, 2, 3]), {}, 0,
False,
[[1], [2], [3]], ["x0"])
# indices must match
t_invalid((pandas.DataFrame([[1]], index=[1]),
pandas.DataFrame([[1]], index=[2])),
{}, 0)
# Foreign ModelDesc factories
class ForeignModelSource(object):
def __patsy_get_model_desc__(self, data):
return ModelDesc([Term([LookupFactor("Y")])],
[Term([LookupFactor("X")])])
foreign_model = ForeignModelSource()
t(foreign_model,
{"Y": [1, 2],
"X": [[1, 2], [3, 4]]},
0,
True,
[[1, 2], [3, 4]], ["X[0]", "X[1]"],
[[1], [2]], ["Y"])
class BadForeignModelSource(object):
def __patsy_get_model_desc__(self, data):
return data
t_invalid(BadForeignModelSource(), {}, 0)
# string formulas
t("y ~ x", {"y": [1, 2], "x": [3, 4]}, 0,
True,
[[1, 3], [1, 4]], ["Intercept", "x"],
[[1], [2]], ["y"])
t("~ x", {"y": [1, 2], "x": [3, 4]}, 0,
True,
[[1, 3], [1, 4]], ["Intercept", "x"])
t("x + y", {"y": [1, 2], "x": [3, 4]}, 0,
True,
[[1, 3, 1], [1, 4, 2]], ["Intercept", "x", "y"])
# ModelDesc
desc = ModelDesc([], [Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5]}, 0,
True,
[[1.5], [2.5], [3.5]], ["x"])
desc = ModelDesc([], [Term([]), Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5]}, 0,
True,
[[1, 1.5], [1, 2.5], [1, 3.5]], ["Intercept", "x"])
desc = ModelDesc([Term([LookupFactor("y")])],
[Term([]), Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5], "y": [10, 20, 30]}, 0,
True,
[[1, 1.5], [1, 2.5], [1, 3.5]], ["Intercept", "x"],
[[10], [20], [30]], ["y"])
# builders
termlists = ([],
[Term([LookupFactor("x")])],
[Term([]), Term([LookupFactor("x")])],
)
builders = design_matrix_builders(termlists,
lambda: iter([{"x": [1, 2, 3]}]))
# twople but with no LHS
t((builders[0], builders[2]), {"x": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"])
# single DesignMatrixBuilder
t(builders[2], {"x": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"])
# twople with LHS
t((builders[1], builders[2]), {"x": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"],
[[10], [20], [30]], ["x"])
# check depth arguments
x_in_env = [1, 2, 3]
t("~ x_in_env", {}, 0,
True,
[[1, 1], [1, 2], [1, 3]], ["Intercept", "x_in_env"])
t("~ x_in_env", {"x_in_env": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x_in_env"])
# Trying to pull x_in_env out of our *caller* shouldn't work.
t_invalid("~ x_in_env", {}, 1, exc=(NameError, PatsyError))
# But then again it should, if called from one down on the stack:
def check_nested_call():
x_in_env = "asdf"
t("~ x_in_env", {}, 1,
True,
[[1, 1], [1, 2], [1, 3]], ["Intercept", "x_in_env"])
check_nested_call()
# passing in an explicit EvalEnvironment also works:
e = EvalEnvironment.capture(1)
t_invalid("~ x_in_env", {}, e, exc=(NameError, PatsyError))
e = EvalEnvironment.capture(0)
def check_nested_call_2():
x_in_env = "asdf"
t("~ x_in_env", {}, e,
True,
[[1, 1], [1, 2], [1, 3]], ["Intercept", "x_in_env"])
check_nested_call_2()
def test_return_pandas():
if not have_pandas:
return
# basic check of pulling a Series out of the environment
s1 = pandas.Series([1, 2, 3], name="AA", index=[10, 20, 30])
s2 = pandas.Series([4, 5, 6], name="BB", index=[10, 20, 30])
df1 = dmatrix("s1", return_type="dataframe")
assert np.allclose(df1, [[1, 1], [1, 2], [1, 3]])
assert np.array_equal(df1.columns, ["Intercept", "s1"])
assert df1.design_info.column_names == ["Intercept", "s1"]
assert np.array_equal(df1.index, [10, 20, 30])
df2, df3 = dmatrices("s2 ~ s1", return_type="dataframe")
assert np.allclose(df2, [[4], [5], [6]])
assert np.array_equal(df2.columns, ["s2"])
assert df2.design_info.column_names == ["s2"]
assert np.array_equal(df2.index, [10, 20, 30])
assert np.allclose(df3, [[1, 1], [1, 2], [1, 3]])
assert np.array_equal(df3.columns, ["Intercept", "s1"])
assert df3.design_info.column_names == ["Intercept", "s1"]
assert np.array_equal(df3.index, [10, 20, 30])
# indices are preserved if pandas is passed in directly
df4 = dmatrix(s1, return_type="dataframe")
assert np.allclose(df4, [[1], [2], [3]])
assert np.array_equal(df4.columns, ["AA"])
assert df4.design_info.column_names == ["AA"]
assert np.array_equal(df4.index, [10, 20, 30])
df5, df6 = dmatrices((s2, s1), return_type="dataframe")
assert np.allclose(df5, [[4], [5], [6]])
assert np.array_equal(df5.columns, ["BB"])
assert df5.design_info.column_names == ["BB"]
assert np.array_equal(df5.index, [10, 20, 30])
assert np.allclose(df6, [[1], [2], [3]])
assert np.array_equal(df6.columns, ["AA"])
assert df6.design_info.column_names == ["AA"]
assert np.array_equal(df6.index, [10, 20, 30])
# Both combinations of with-index and without-index
df7, df8 = dmatrices((s1, [10, 11, 12]), return_type="dataframe")
assert np.array_equal(df7.index, s1.index)
assert np.array_equal(df8.index, s1.index)
df9, df10 = dmatrices(([10, 11, 12], s1), return_type="dataframe")
assert np.array_equal(df9.index, s1.index)
assert np.array_equal(df10.index, s1.index)
# pandas must be available
import patsy.highlevel
had_pandas = patsy.highlevel.have_pandas
try:
patsy.highlevel.have_pandas = False
assert_raises(PatsyError,
dmatrix, "x", {"x": [1]}, 0, return_type="dataframe")
assert_raises(PatsyError,
dmatrices, "y ~ x", {"x": [1], "y": [2]}, 0,
return_type="dataframe")
finally:
patsy.highlevel.have_pandas = had_pandas
def test_term_info():
data = balanced(a=2, b=2)
rhs = dmatrix("a:b", data)
assert rhs.design_info.column_names == ["Intercept", "b[T.b2]",
"a[T.a2]:b[b1]", "a[T.a2]:b[b2]"]
assert rhs.design_info.term_names == ["Intercept", "a:b"]
assert len(rhs.design_info.terms) == 2
assert rhs.design_info.terms[0] == INTERCEPT
def test_data_types():
data = {"a": [1, 2, 3],
"b": [1.0, 2.0, 3.0],
"c": np.asarray([1, 2, 3], dtype=np.float32),
"d": [True, False, True],
"e": ["foo", "bar", "baz"],
"f": C([1, 2, 3]),
"g": C(["foo", "bar", "baz"]),
"h": np.array(["foo", 1, (1, "hi")], dtype=object),
}
t("~ 0 + a", data, 0, True,
[[1], [2], [3]], ["a"])
t("~ 0 + b", data, 0, True,
[[1], [2], [3]], ["b"])
t("~ 0 + c", data, 0, True,
[[1], [2], [3]], ["c"])
t("~ 0 + d", data, 0, True,
[[0, 1], [1, 0], [0, 1]], ["d[False]", "d[True]"])
t("~ 0 + e", data, 0, True,
[[0, 0, 1], [1, 0, 0], [0, 1, 0]], ["e[bar]", "e[baz]", "e[foo]"])
t("~ 0 + f", data, 0, True,
[[1, 0, 0], [0, 1, 0], [0, 0, 1]], ["f[1]", "f[2]", "f[3]"])
t("~ 0 + g", data, 0, True,
[[0, 0, 1], [1, 0, 0], [0, 1, 0]], ["g[bar]", "g[baz]", "g[foo]"])
# This depends on Python's sorting behavior:
t("~ 0 + h", data, 0, True,
[[0, 1, 0], [1, 0, 0], [0, 0, 1]],
["h[1]", "h[foo]", "h[(1, 'hi')]"])
def test_categorical():
data = balanced(a=2, b=2)
# There are more exhaustive tests for all the different coding options in
# test_build; let's just make sure that C() and stuff works.
t("~ C(a)", data, 0,
True,
[[1, 0], [1, 0], [1, 1], [1, 1]], ["Intercept", "C(a)[T.a2]"])
t("~ C(a, levels=['a2', 'a1'])", data, 0,
True,
[[1, 1], [1, 1], [1, 0], [1, 0]],
["Intercept", "C(a, levels=['a2', 'a1'])[T.a1]"])
t("~ C(a, Treatment(reference=-1))", data, 0,
True,
[[1, 1], [1, 1], [1, 0], [1, 0]],
["Intercept", "C(a, Treatment(reference=-1))[T.a1]"])
# Different interactions
t("a*b", data, 0,
True,
[[1, 0, 0, 0],
[1, 0, 1, 0],
[1, 1, 0, 0],
[1, 1, 1, 1]],
["Intercept", "a[T.a2]", "b[T.b2]", "a[T.a2]:b[T.b2]"])
t("0 + a:b", data, 0,
True,
[[1, 0, 0, 0],
[0, 0, 1, 0],
[0, 1, 0, 0],
[0, 0, 0, 1]],
["a[a1]:b[b1]", "a[a2]:b[b1]", "a[a1]:b[b2]", "a[a2]:b[b2]"])
t("1 + a + a:b", data, 0,
True,
[[1, 0, 0, 0],
[1, 0, 1, 0],
[1, 1, 0, 0],
[1, 1, 0, 1]],
["Intercept", "a[T.a2]", "a[a1]:b[T.b2]", "a[a2]:b[T.b2]"])
# Changing contrast with C()
data["a"] = C(data["a"], Helmert)
t("a", data, 0,
True,
[[1, -1], [1, -1], [1, 1], [1, 1]], ["Intercept", "a[H.a2]"])
t("C(a, Treatment)", data, 0,
True,
[[1, 0], [1, 0], [1, 1], [1, 1]], ["Intercept", "C(a, Treatment)[T.a2]"])
# That didn't affect the original object
t("a", data, 0,
True,
[[1, -1], [1, -1], [1, 1], [1, 1]], ["Intercept", "a[H.a2]"])
def test_builtins():
data = {"x": [1, 2, 3],
"y": [4, 5, 6],
"a b c": [10, 20, 30]}
t("0 + I(x + y)", data, 0,
True,
[[1], [2], [3], [4], [5], [6]], ["I(x + y)"])
t("Q('a b c')", data, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "Q('a b c')"])
t("center(x)", data, 0,
True,
[[1, -1], [1, 0], [1, 1]], ["Intercept", "center(x)"])
def test_incremental():
# incr_dbuilder(s)
# stateful transformations
datas = [
{"a": ["a2", "a2", "a2"],
"x": [1, 2, 3]},
{"a": ["a2", "a2", "a1"],
"x": [4, 5, 6]},
]
x = np.asarray([1, 2, 3, 4, 5, 6])
sin_center_x = np.sin(x - np.mean(x))
x_col = sin_center_x - np.mean(sin_center_x)
def data_iter_maker():
return iter(datas)
builders = incr_dbuilders("1 ~ a + center(np.sin(center(x)))",
data_iter_maker)
lhs, rhs = build_design_matrices(builders, datas[1])
assert lhs.design_info.column_names == ["Intercept"]
assert rhs.design_info.column_names == ["Intercept",
"a[T.a2]",
"center(np.sin(center(x)))"]
assert np.allclose(lhs, [[1], [1], [1]])
assert np.allclose(rhs, np.column_stack(([1, 1, 1],
[1, 1, 0],
x_col[3:])))
builder = incr_dbuilder("~ a + center(np.sin(center(x)))",
data_iter_maker)
(rhs,) = build_design_matrices([builder], datas[1])
assert rhs.design_info.column_names == ["Intercept",
"a[T.a2]",
"center(np.sin(center(x)))"]
assert np.allclose(lhs, [[1], [1], [1]])
assert np.allclose(rhs, np.column_stack(([1, 1, 1],
[1, 1, 0],
x_col[3:])))
assert_raises(PatsyError, incr_dbuilder, "x ~ x", data_iter_maker)
assert_raises(PatsyError, incr_dbuilders, "x", data_iter_maker)
def test_env_transform():
t("~ np.sin(x)", {"x": [1, 2, 3]}, 0,
True,
[[1, np.sin(1)], [1, np.sin(2)], [1, np.sin(3)]],
["Intercept", "np.sin(x)"])
# Term ordering:
# 1) all 0-order no-numeric
# 2) all 1st-order no-numeric
# 3) all 2nd-order no-numeric
# 4) ...
# 5) all 0-order with the first numeric interaction encountered
# 6) all 1st-order with the first numeric interaction encountered
# 7) ...
# 8) all 0-order with the second numeric interaction encountered
# 9) ...
def test_term_order():
data = balanced(a=2, b=2)
data["x1"] = np.linspace(0, 1, 4)
data["x2"] = data["x1"] ** 2
def t_terms(formula, order):
m = dmatrix(formula, data)
assert m.design_info.term_names == order
t_terms("a + b + x1 + x2", ["Intercept", "a", "b", "x1", "x2"])
t_terms("b + a + x2 + x1", ["Intercept", "b", "a", "x2", "x1"])
t_terms("0 + x1 + a + x2 + b + 1", ["Intercept", "a", "b", "x1", "x2"])
t_terms("0 + a:b + a + b + 1", ["Intercept", "a", "b", "a:b"])
t_terms("a + a:x1 + x2 + x1 + b",
["Intercept", "a", "b", "x1", "a:x1", "x2"])
t_terms("0 + a:x1:x2 + a + x2:x1:b + x2 + x1 + a:x1 + x1:x2 + x1:a:x2:a:b",
["a",
"x1:x2", "a:x1:x2", "x2:x1:b", "x1:a:x2:b",
"x2",
"x1",
"a:x1"])
def _check_division(expect_true_division): # pragma: no cover
# We evaluate the formula "I(x / y)" in our *caller's* scope, so the
# result depends on whether our caller has done 'from __future__ import
# division'.
data = {"x": 5, "y": 2}
m = dmatrix("0 + I(x / y)", data, 1)
if expect_true_division:
assert np.allclose(m, [[2.5]])
else:
assert np.allclose(m, [[2]])
def test_future():
if __future__.division.getMandatoryRelease() < sys.version_info:
# This is Python 3, where division is already default
return
# no __future__.division in this module's scope
_check_division(False)
# create an execution context where __future__.division is in effect
exec ("from __future__ import division\n"
"_check_division(True)\n")
def test_multicolumn():
data = {
"a": ["a1", "a2"],
"X": [[1, 2], [3, 4]],
"Y": [[1, 3], [2, 4]],
}
t("X*Y", data, 0,
True,
[[1, 1, 2, 1, 3, 1 * 1, 2 * 1, 1 * 3, 2 * 3],
[1, 3, 4, 2, 4, 3 * 2, 4 * 2, 3 * 4, 4 * 4]],
["Intercept", "X[0]", "X[1]", "Y[0]", "Y[1]",
"X[0]:Y[0]", "X[1]:Y[0]", "X[0]:Y[1]", "X[1]:Y[1]"])
t("a:X + Y", data, 0,
True,
[[1, 1, 0, 2, 0, 1, 3],
[1, 0, 3, 0, 4, 2, 4]],
["Intercept",
"a[a1]:X[0]", "a[a2]:X[0]", "a[a1]:X[1]", "a[a2]:X[1]",
"Y[0]", "Y[1]"])
def test_dmatrix_dmatrices_no_data():
x = [1, 2, 3]
y = [4, 5, 6]
assert np.allclose(dmatrix("x"), [[1, 1], [1, 2], [1, 3]])
lhs, rhs = dmatrices("y ~ x")
assert np.allclose(lhs, [[4], [5], [6]])
assert np.allclose(rhs, [[1, 1], [1, 2], [1, 3]])
def test_designinfo_describe():
lhs, rhs = dmatrices("y ~ x + a", {"y": [1, 2, 3],
"x": [4, 5, 6],
"a": ["a1", "a2", "a3"]})
assert lhs.design_info.describe() == "y"
assert rhs.design_info.describe() == "1 + a + x"
def test_evalfactor_reraise():
# This will produce a PatsyError, but buried inside the factor evaluation,
# so the original code has no way to give it an appropriate origin=
# attribute. EvalFactor should notice this, and add a useful origin:
def raise_patsy_error(x):
raise PatsyError("WHEEEEEE")
formula = "raise_patsy_error(X) + Y"
try:
dmatrix(formula, {"X": [1, 2, 3], "Y": [4, 5, 6]})
except PatsyError, e:
assert e.origin == Origin(formula, 0, formula.index(" "))
else:
assert False
# This will produce a KeyError, which on Python 3 we can do wrap without
# destroying the traceback, so we do so. On Python 2 we let the original
# exception escape.
try:
dmatrix("1 + x[1]", {"x": {}})
except Exception, e:
if sys.version_info[0] >= 3:
assert isinstance(e, PatsyError)
assert e.origin == Origin("1 + x[1]", 4, 8)
else:
assert isinstance(e, KeyError)
else:
assert False
def test_dmatrix_NA_action():
data = {"x": [1, 2, 3, np.nan], "y": [np.nan, 20, 30, 40]}
return_types = ["matrix"]
if have_pandas:
return_types.append("dataframe")
for return_type in return_types:
mat = dmatrix("x + y", data=data, return_type=return_type)
assert np.array_equal(mat, [[1, 2, 20],
[1, 3, 30]])
if return_type == "dataframe":
assert mat.index.equals([1, 2])
assert_raises(PatsyError, dmatrix, "x + y", data=data,
return_type=return_type,
NA_action="raise")
lmat, rmat = dmatrices("y ~ x", data=data, return_type=return_type)
assert np.array_equal(lmat, [[20], [30]])
assert np.array_equal(rmat, [[1, 2], [1, 3]])
if return_type == "dataframe":
assert lmat.index.equals([1, 2])
assert rmat.index.equals([1, 2])
assert_raises(PatsyError,
dmatrices, "y ~ x", data=data, return_type=return_type,
NA_action="raise")
# Initial release for the NA handling code had problems with
# non-data-dependent matrices like "~ 1".
lmat, rmat = dmatrices("y ~ 1", data=data, return_type=return_type)
assert np.array_equal(lmat, [[20], [30], [40]])
assert np.array_equal(rmat, [[1], [1], [1]])
if return_type == "dataframe":
assert lmat.index.equals([1, 2, 3])
assert rmat.index.equals([1, 2, 3])
assert_raises(PatsyError,
dmatrices, "y ~ 1", data=data, return_type=return_type,
NA_action="raise")
|