Repository navigation
Expand file tree
/
Copy path__init__.py
More file actions
214 lines (186 loc) · 5.77 KB
/
Copy path__init__.py
File metadata and controls
214 lines (186 loc) · 5.77 KB
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
# 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.
"""DataFusion: an in-process query engine built on Apache Arrow.
DataFusion is not a database -- it has no server and no external dependencies.
You create a :py:class:`SessionContext`, point it at data sources (Parquet, CSV,
JSON, Arrow IPC, Pandas, Polars, or raw Python dicts/lists), and run queries
using either SQL or the DataFrame API.
Core abstractions
-----------------
- **SessionContext** -- entry point for loading data, running SQL, and creating
DataFrames.
- **DataFrame** -- lazy query builder. Every method returns a new DataFrame;
call :py:meth:`~datafusion.dataframe.DataFrame.collect` or a ``to_*``
method to execute.
- **Expr** -- expression tree node for column references, literals, and function
calls. Build with :py:func:`col` and :py:func:`lit`.
- **functions** -- 290+ built-in scalar, aggregate, and window functions.
Quick start
-----------
>>> from datafusion import SessionContext, col
>>> from datafusion import functions as F
>>> ctx = SessionContext()
>>> df = ctx.from_pydict({"a": [1, 2, 3], "b": [4, 5, 6]})
>>> result = (
... df.filter(col("a") > 1)
... .with_column("total", col("a") + col("b"))
... .aggregate([], [F.sum(col("total")).alias("grand_total")])
... )
>>> result.to_pydict()
{'grand_total': [16]}
User guide and full documentation: https://datafusion.apache.org/python
AI agent reference (SQL-to-DataFrame mappings, expression-building patterns,
common pitfalls), written in a dense, skill-oriented format:
https://github.com/apache/datafusion-python/blob/main/skills/datafusion_python/SKILL.md
"""
from __future__ import annotations
from typing import Any
try:
import importlib.metadata as importlib_metadata
except ImportError:
import importlib_metadata # type: ignore[import]
# Public submodules
from . import functions, ipc, object_store, substrait, unparser
# The following imports are okay to remain as opaque to the user.
from .catalog import (
Catalog,
Table,
TableProviderFactory,
TableProviderFactoryExportable,
)
from .col import col, column
from .common import DFSchema
from .context import (
RuntimeEnvBuilder,
SessionConfig,
SessionContext,
SQLOptions,
)
from .dataframe import (
DataFrame,
DataFrameWriteOptions,
ExplainFormat,
InsertOp,
ParquetColumnOptions,
ParquetWriterOptions,
)
from .dataframe_formatter import configure_formatter
from .expr import Expr, WindowFrame
from .extensions import (
QueryPlannerExportable,
SessionComponentsExportable,
SessionExtensionComponents,
SessionPlannerExportable,
)
from .io import read_avro, read_csv, read_json, read_parquet
from .options import CsvReadOptions
from .plan import ExecutionPlan, LogicalPlan, Metric, MetricsSet
from .record_batch import RecordBatch, RecordBatchStream
from .user_defined import (
Accumulator,
AggregateUDF,
ScalarUDF,
TableFunction,
WindowUDF,
udaf,
udf,
udtf,
udwf,
)
__version__ = importlib_metadata.version(__name__)
__all__ = [
"Accumulator",
"AggregateUDF",
"Catalog",
"CsvReadOptions",
"DFSchema",
"DataFrame",
"DataFrameWriteOptions",
"ExecutionPlan",
"ExplainFormat",
"Expr",
"InsertOp",
"LogicalPlan",
"Metric",
"MetricsSet",
"ParquetColumnOptions",
"ParquetWriterOptions",
"QueryPlannerExportable",
"RecordBatch",
"RecordBatchStream",
"RuntimeEnvBuilder",
"SQLOptions",
"ScalarUDF",
"SessionComponentsExportable",
"SessionConfig",
"SessionContext",
"SessionExtensionComponents",
"SessionPlannerExportable",
"Table",
"TableFunction",
"TableProviderFactory",
"TableProviderFactoryExportable",
"WindowFrame",
"WindowUDF",
"catalog",
"col",
"column",
"common",
"configure_formatter",
"expr",
"extensions",
"functions",
"ipc",
"lit",
"literal",
"object_store",
"options",
"read_avro",
"read_csv",
"read_json",
"read_parquet",
"substrait",
"udaf",
"udf",
"udtf",
"udwf",
"unparser",
]
def literal(value: Any) -> Expr:
"""Create a literal expression."""
return Expr.literal(value)
def string_literal(value: str) -> Expr:
"""Create a UTF8 literal expression.
It differs from `literal` which creates a UTF8view literal.
"""
return Expr.string_literal(value)
def str_lit(value: str) -> Expr:
"""Alias for `string_literal`."""
return string_literal(value)
def lit(value: Any) -> Expr:
"""Create a literal expression."""
return Expr.literal(value)
def literal_with_metadata(value: Any, metadata: dict[str, str]) -> Expr:
"""Creates a new expression representing a scalar value with metadata.
Args:
value: A valid PyArrow scalar value or easily castable to one.
metadata: Metadata to attach to the expression.
"""
return Expr.literal_with_metadata(value, metadata)
def lit_with_metadata(value: Any, metadata: dict[str, str]) -> Expr:
"""Alias for literal_with_metadata."""
return literal_with_metadata(value, metadata)