File size: 8,796 Bytes
9c6594c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

# pandas lazy-loading API shim that reduces API call and import overhead

import warnings
from threading import Lock


cdef class _PandasAPIShim(object):
    """
    Lazy pandas importer that isolates usages of pandas APIs and avoids
    importing pandas until it's actually needed
    """
    cdef:
        bint _tried_importing_pandas
        bint _have_pandas

    cdef readonly:
        object _loose_version, _version
        object _pd, _types_api, _compat_module
        object _data_frame, _index, _series, _categorical_type
        object _datetimetz_type, _extension_array, _extension_dtype
        object _array_like_types, _is_extension_array_dtype, _lock
        bint has_sparse
        bint _pd024
        bint _is_v1, _is_ge_v21, _is_ge_v23, _is_ge_v3, _is_ge_v3_strict

    def __init__(self):
        self._lock = Lock()
        self._tried_importing_pandas = False
        self._have_pandas = 0

    cdef _import_pandas(self, bint raise_):
        try:
            import pandas as pd
            import pyarrow.pandas_compat as pdcompat
        except ImportError:
            self._have_pandas = False
            if raise_:
                raise
            else:
                return

        from pyarrow.vendored.version import Version

        self._pd = pd
        self._version = pd.__version__
        self._loose_version = Version(pd.__version__)
        self._is_v1 = False

        if self._loose_version < Version('1.0.0'):
            self._have_pandas = False
            if raise_:
                raise ImportError(
                    "pyarrow requires pandas 1.0.0 or above, pandas {} is "
                    "installed".format(self._version)
                )
            else:
                warnings.warn(
                    "pyarrow requires pandas 1.0.0 or above, pandas {} is "
                    "installed. Therefore, pandas-specific integration is not "
                    "used.".format(self._version), stacklevel=2)
                return

        self._is_v1 = self._loose_version < Version('2.0.0')
        self._is_ge_v21 = self._loose_version >= Version('2.1.0')
        self._is_ge_v23 = self._loose_version >= Version('2.3.0.dev0')
        self._is_ge_v3 = self._loose_version >= Version('3.0.0.dev0')
        self._is_ge_v3_strict = self._loose_version >= Version('3.0.0')

        self._compat_module = pdcompat
        self._data_frame = pd.DataFrame
        self._index = pd.Index
        self._categorical_type = pd.Categorical
        self._series = pd.Series
        self._extension_array = pd.api.extensions.ExtensionArray
        self._array_like_types = (
            self._series, self._index, self._categorical_type,
            self._extension_array)
        self._extension_dtype = pd.api.extensions.ExtensionDtype
        self._is_extension_array_dtype = (
            pd.api.types.is_extension_array_dtype)
        self._types_api = pd.api.types
        self._datetimetz_type = pd.api.types.DatetimeTZDtype
        self._have_pandas = True
        self.has_sparse = False

    cdef inline _check_import(self, bint raise_=True):
        if not self._tried_importing_pandas:
            with self._lock:
                if not self._tried_importing_pandas:
                    try:
                        self._import_pandas(raise_)
                    finally:
                        self._tried_importing_pandas = True
                    return

        if not self._have_pandas and raise_:
            self._import_pandas(raise_)

    def series(self, *args, **kwargs):
        self._check_import()
        return self._series(*args, **kwargs)

    def data_frame(self, *args, **kwargs):
        self._check_import()
        return self._data_frame(*args, **kwargs)

    cdef inline bint _have_pandas_internal(self):
        if not self._tried_importing_pandas:
            self._check_import(raise_=False)
        return self._have_pandas

    @property
    def have_pandas(self):
        return self._have_pandas_internal()

    @property
    def compat(self):
        self._check_import()
        return self._compat_module

    @property
    def pd(self):
        self._check_import()
        return self._pd

    cpdef infer_dtype(self, obj):
        self._check_import()
        try:
            return self._types_api.infer_dtype(obj, skipna=False)
        except AttributeError:
            return self._pd.lib.infer_dtype(obj)

    cpdef pandas_dtype(self, dtype):
        self._check_import()
        try:
            return self._types_api.pandas_dtype(dtype)
        except AttributeError:
            return None

    @property
    def loose_version(self):
        self._check_import()
        return self._loose_version

    @property
    def version(self):
        self._check_import()
        return self._version

    def is_v1(self):
        self._check_import()
        return self._is_v1

    def is_ge_v21(self):
        self._check_import()
        return self._is_ge_v21

    def is_ge_v23(self):
        self._check_import()
        return self._is_ge_v23

    def is_ge_v3(self):
        self._check_import()
        return self._is_ge_v3

    def is_ge_v3_strict(self):
        self._check_import()
        return self._is_ge_v3_strict

    def uses_string_dtype(self):
        if self.is_ge_v3_strict():
            return True
        try:
            if self.is_ge_v23() and self.pd.options.future.infer_string:
                return True
        except:
            pass
        return False

    @property
    def categorical_type(self):
        self._check_import()
        return self._categorical_type

    @property
    def datetimetz_type(self):
        self._check_import()
        return self._datetimetz_type

    @property
    def extension_dtype(self):
        self._check_import()
        return self._extension_dtype

    cpdef is_array_like(self, obj):
        self._check_import()
        return isinstance(obj, self._array_like_types)

    cpdef is_categorical(self, obj):
        if self._have_pandas_internal():
            return isinstance(obj, self._categorical_type)
        else:
            return False

    cpdef is_datetimetz(self, obj):
        if self._have_pandas_internal():
            return isinstance(obj, self._datetimetz_type)
        else:
            return False

    cpdef is_extension_array_dtype(self, obj):
        self._check_import()
        if self._is_extension_array_dtype:
            return self._is_extension_array_dtype(obj)
        else:
            return False

    cpdef is_sparse(self, obj):
        if self._have_pandas_internal():
            return isinstance(obj.dtype, self.pd.SparseDtype)
        else:
            return False

    cpdef is_data_frame(self, obj):
        if self._have_pandas_internal():
            return isinstance(obj, self._data_frame)
        else:
            return False

    cpdef is_series(self, obj):
        if self._have_pandas_internal():
            return isinstance(obj, self._series)
        else:
            return False

    cpdef is_index(self, obj):
        if self._have_pandas_internal():
            return isinstance(obj, self._index)
        else:
            return False

    cpdef get_values(self, obj):
        """
        Get the underlying array values of a pandas Series or Index in the
        format (np.ndarray or pandas ExtensionArray) as we need them.

        Assumes obj is a pandas Series or Index.
        """
        self._check_import()
        if isinstance(obj.dtype, (self.pd.api.types.IntervalDtype,
                                  self.pd.api.types.PeriodDtype)):
            return obj.array
        return obj.values

    def get_rangeindex_attribute(self, level, name):
        # public start/stop/step attributes added in pandas 0.25.0
        self._check_import()
        if hasattr(level, name):
            return getattr(level, name)
        return getattr(level, '_' + name)


cdef _PandasAPIShim pandas_api = _PandasAPIShim()
_pandas_api = pandas_api