Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/pandas/__init__.py: 22%
Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1from __future__ import annotations
3import os
4import warnings
6__docformat__ = "restructuredtext"
8# Let users know if they're missing any of our hard dependencies
9_hard_dependencies = ("numpy", "pytz", "dateutil")
10_missing_dependencies = []
12for _dependency in _hard_dependencies:
13 try:
14 __import__(_dependency)
15 except ImportError as _e: # pragma: no cover
16 _missing_dependencies.append(f"{_dependency}: {_e}")
18if _missing_dependencies: # pragma: no cover
19 raise ImportError(
20 "Unable to import required dependencies:\n" + "\n".join(_missing_dependencies)
21 )
22del _hard_dependencies, _dependency, _missing_dependencies
24try:
25 # numpy compat
26 from pandas.compat import (
27 is_numpy_dev as _is_numpy_dev, # pyright: ignore[reportUnusedImport] # noqa: F401
28 )
29except ImportError as _err: # pragma: no cover
30 _module = _err.name
31 raise ImportError(
32 f"C extension: {_module} not built. If you want to import "
33 "pandas from the source directory, you may need to run "
34 "'python setup.py build_ext' to build the C extensions first."
35 ) from _err
37from pandas._config import (
38 get_option,
39 set_option,
40 reset_option,
41 describe_option,
42 option_context,
43 options,
44)
46# let init-time option registration happen
47import pandas.core.config_init # pyright: ignore[reportUnusedImport] # noqa: F401
49from pandas.core.api import (
50 # dtype
51 ArrowDtype,
52 Int8Dtype,
53 Int16Dtype,
54 Int32Dtype,
55 Int64Dtype,
56 UInt8Dtype,
57 UInt16Dtype,
58 UInt32Dtype,
59 UInt64Dtype,
60 Float32Dtype,
61 Float64Dtype,
62 CategoricalDtype,
63 PeriodDtype,
64 IntervalDtype,
65 DatetimeTZDtype,
66 StringDtype,
67 BooleanDtype,
68 # missing
69 NA,
70 isna,
71 isnull,
72 notna,
73 notnull,
74 # indexes
75 Index,
76 CategoricalIndex,
77 RangeIndex,
78 MultiIndex,
79 IntervalIndex,
80 TimedeltaIndex,
81 DatetimeIndex,
82 PeriodIndex,
83 IndexSlice,
84 # tseries
85 NaT,
86 Period,
87 period_range,
88 Timedelta,
89 timedelta_range,
90 Timestamp,
91 date_range,
92 bdate_range,
93 Interval,
94 interval_range,
95 DateOffset,
96 # conversion
97 to_numeric,
98 to_datetime,
99 to_timedelta,
100 # misc
101 Flags,
102 Grouper,
103 factorize,
104 unique,
105 value_counts,
106 NamedAgg,
107 array,
108 Categorical,
109 set_eng_float_format,
110 Series,
111 DataFrame,
112)
114from pandas.core.dtypes.dtypes import SparseDtype
116from pandas.tseries.api import infer_freq
117from pandas.tseries import offsets
119from pandas.core.computation.api import eval
121from pandas.core.reshape.api import (
122 concat,
123 lreshape,
124 melt,
125 wide_to_long,
126 merge,
127 merge_asof,
128 merge_ordered,
129 crosstab,
130 pivot,
131 pivot_table,
132 get_dummies,
133 from_dummies,
134 cut,
135 qcut,
136)
138from pandas import api, arrays, errors, io, plotting, tseries
139from pandas import testing
140from pandas.util._print_versions import show_versions
142from pandas.io.api import (
143 # excel
144 ExcelFile,
145 ExcelWriter,
146 read_excel,
147 # parsers
148 read_csv,
149 read_fwf,
150 read_table,
151 # pickle
152 read_pickle,
153 to_pickle,
154 # pytables
155 HDFStore,
156 read_hdf,
157 # sql
158 read_sql,
159 read_sql_query,
160 read_sql_table,
161 # misc
162 read_clipboard,
163 read_parquet,
164 read_orc,
165 read_feather,
166 read_gbq,
167 read_html,
168 read_xml,
169 read_json,
170 read_stata,
171 read_sas,
172 read_spss,
173)
175from pandas.io.json._normalize import json_normalize
177from pandas.util._tester import test
179# use the closest tagged version if possible
180_built_with_meson = False
181try:
182 from pandas._version_meson import ( # pyright: ignore [reportMissingImports]
183 __version__,
184 __git_version__,
185 )
187 _built_with_meson = True
188except ImportError:
189 from pandas._version import get_versions
191 v = get_versions()
192 __version__ = v.get("closest-tag", v["version"])
193 __git_version__ = v.get("full-revisionid")
194 del get_versions, v
196# GH#55043 - deprecation of the data_manager option
197if "PANDAS_DATA_MANAGER" in os.environ:
198 warnings.warn(
199 "The env variable PANDAS_DATA_MANAGER is set. The data_manager option is "
200 "deprecated and will be removed in a future version. Only the BlockManager "
201 "will be available. Unset this environment variable to silence this warning.",
202 FutureWarning,
203 stacklevel=2,
204 )
206del warnings, os
208# module level doc-string
209__doc__ = """
210pandas - a powerful data analysis and manipulation library for Python
211=====================================================================
213**pandas** is a Python package providing fast, flexible, and expressive data
214structures designed to make working with "relational" or "labeled" data both
215easy and intuitive. It aims to be the fundamental high-level building block for
216doing practical, **real world** data analysis in Python. Additionally, it has
217the broader goal of becoming **the most powerful and flexible open source data
218analysis / manipulation tool available in any language**. It is already well on
219its way toward this goal.
221Main Features
222-------------
223Here are just a few of the things that pandas does well:
225 - Easy handling of missing data in floating point as well as non-floating
226 point data.
227 - Size mutability: columns can be inserted and deleted from DataFrame and
228 higher dimensional objects
229 - Automatic and explicit data alignment: objects can be explicitly aligned
230 to a set of labels, or the user can simply ignore the labels and let
231 `Series`, `DataFrame`, etc. automatically align the data for you in
232 computations.
233 - Powerful, flexible group by functionality to perform split-apply-combine
234 operations on data sets, for both aggregating and transforming data.
235 - Make it easy to convert ragged, differently-indexed data in other Python
236 and NumPy data structures into DataFrame objects.
237 - Intelligent label-based slicing, fancy indexing, and subsetting of large
238 data sets.
239 - Intuitive merging and joining data sets.
240 - Flexible reshaping and pivoting of data sets.
241 - Hierarchical labeling of axes (possible to have multiple labels per tick).
242 - Robust IO tools for loading data from flat files (CSV and delimited),
243 Excel files, databases, and saving/loading data from the ultrafast HDF5
244 format.
245 - Time series-specific functionality: date range generation and frequency
246 conversion, moving window statistics, date shifting and lagging.
247"""
249# Use __all__ to let type checkers know what is part of the public API.
250# Pandas is not (yet) a py.typed library: the public API is determined
251# based on the documentation.
252__all__ = [
253 "ArrowDtype",
254 "BooleanDtype",
255 "Categorical",
256 "CategoricalDtype",
257 "CategoricalIndex",
258 "DataFrame",
259 "DateOffset",
260 "DatetimeIndex",
261 "DatetimeTZDtype",
262 "ExcelFile",
263 "ExcelWriter",
264 "Flags",
265 "Float32Dtype",
266 "Float64Dtype",
267 "Grouper",
268 "HDFStore",
269 "Index",
270 "IndexSlice",
271 "Int16Dtype",
272 "Int32Dtype",
273 "Int64Dtype",
274 "Int8Dtype",
275 "Interval",
276 "IntervalDtype",
277 "IntervalIndex",
278 "MultiIndex",
279 "NA",
280 "NaT",
281 "NamedAgg",
282 "Period",
283 "PeriodDtype",
284 "PeriodIndex",
285 "RangeIndex",
286 "Series",
287 "SparseDtype",
288 "StringDtype",
289 "Timedelta",
290 "TimedeltaIndex",
291 "Timestamp",
292 "UInt16Dtype",
293 "UInt32Dtype",
294 "UInt64Dtype",
295 "UInt8Dtype",
296 "api",
297 "array",
298 "arrays",
299 "bdate_range",
300 "concat",
301 "crosstab",
302 "cut",
303 "date_range",
304 "describe_option",
305 "errors",
306 "eval",
307 "factorize",
308 "get_dummies",
309 "from_dummies",
310 "get_option",
311 "infer_freq",
312 "interval_range",
313 "io",
314 "isna",
315 "isnull",
316 "json_normalize",
317 "lreshape",
318 "melt",
319 "merge",
320 "merge_asof",
321 "merge_ordered",
322 "notna",
323 "notnull",
324 "offsets",
325 "option_context",
326 "options",
327 "period_range",
328 "pivot",
329 "pivot_table",
330 "plotting",
331 "qcut",
332 "read_clipboard",
333 "read_csv",
334 "read_excel",
335 "read_feather",
336 "read_fwf",
337 "read_gbq",
338 "read_hdf",
339 "read_html",
340 "read_json",
341 "read_orc",
342 "read_parquet",
343 "read_pickle",
344 "read_sas",
345 "read_spss",
346 "read_sql",
347 "read_sql_query",
348 "read_sql_table",
349 "read_stata",
350 "read_table",
351 "read_xml",
352 "reset_option",
353 "set_eng_float_format",
354 "set_option",
355 "show_versions",
356 "test",
357 "testing",
358 "timedelta_range",
359 "to_datetime",
360 "to_numeric",
361 "to_pickle",
362 "to_timedelta",
363 "tseries",
364 "unique",
365 "value_counts",
366 "wide_to_long",
367]