File size: 11,361 Bytes
fcaa164 |
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 |
# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
# Licensed 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.
# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
import os
from functools import wraps
from pathlib import Path
from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Union
import pandas as pd
if TYPE_CHECKING:
from pandas import DataFrame
from pandasai import SmartDataframe
def check_suffix(valid_suffixs: List[str]) -> Callable:
r"""A decorator to check the file suffix of a given file path.
Args:
valid_suffix (str): The required file suffix.
Returns:
Callable: The decorator function.
"""
def decorator(func: Callable):
@wraps(func)
def wrapper(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
suffix = Path(file_path).suffix
if suffix not in valid_suffixs:
raise ValueError(
f"Only {', '.join(valid_suffixs)} files are supported"
)
return func(self, file_path, *args, **kwargs)
return wrapper
return decorator
class PandaReader:
def __init__(self, config: Optional[Dict[str, Any]] = None) -> None:
r"""Initializes the PandaReader class.
Args:
config (Optional[Dict[str, Any]], optional): The configuration
dictionary that can include LLM API settings for LLM-based
processing. If not provided, it will use OpenAI with the API
key from the OPENAI_API_KEY environment variable. You can
customize the LLM configuration by providing a 'llm' key in
the config dictionary. (default: :obj:`None`)
"""
from pandasai.llm import OpenAI # type: ignore[import-untyped]
self.config = config or {}
if "llm" not in self.config:
self.config["llm"] = OpenAI(
api_token=os.getenv("OPENAI_API_KEY"),
)
self.__LOADER = {
".csv": self.read_csv,
".xlsx": self.read_excel,
".xls": self.read_excel,
".json": self.read_json,
".parquet": self.read_parquet,
".sql": self.read_sql,
".html": self.read_html,
".feather": self.read_feather,
".dta": self.read_stata,
".sas": self.read_sas,
".pkl": self.read_pickle,
".h5": self.read_hdf,
".orc": self.read_orc,
}
def load(
self,
data: Union["DataFrame", str],
*args: Any,
**kwargs: Dict[str, Any],
) -> "SmartDataframe":
r"""Loads a file or DataFrame and returns a SmartDataframe object.
args:
data (Union[DataFrame, str]): The data to load.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
SmartDataframe: The SmartDataframe object.
"""
from pandas import DataFrame
from pandasai import SmartDataframe
if isinstance(data, DataFrame):
return SmartDataframe(data, config=self.config)
file_path = str(data)
path = Path(file_path)
if not file_path.startswith("http") and not path.exists():
raise FileNotFoundError(f"File {file_path} not found")
if path.suffix in self.__LOADER:
return SmartDataframe(
self.__LOADER[path.suffix](file_path, *args, **kwargs), # type: ignore[operator]
config=self.config,
)
else:
raise ValueError(f"Unsupported file format: {path.suffix}")
@check_suffix([".csv"])
def read_csv(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a CSV file and returns a DataFrame.
Args:
file_path (str): The path to the CSV file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_csv(file_path, *args, **kwargs)
@check_suffix([".xlsx", ".xls"])
def read_excel(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads an Excel file and returns a DataFrame.
Args:
file_path (str): The path to the Excel file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_excel(file_path, *args, **kwargs)
@check_suffix([".json"])
def read_json(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a JSON file and returns a DataFrame.
Args:
file_path (str): The path to the JSON file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_json(file_path, *args, **kwargs)
@check_suffix([".parquet"])
def read_parquet(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a Parquet file and returns a DataFrame.
Args:
file_path (str): The path to the Parquet file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_parquet(file_path, *args, **kwargs)
def read_sql(self, *args: Any, **kwargs: Dict[str, Any]) -> "DataFrame":
r"""Reads a SQL file and returns a DataFrame.
Args:
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_sql(*args, **kwargs)
def read_table(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a table and returns a DataFrame.
Args:
file_path (str): The path to the table.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_table(file_path, *args, **kwargs)
def read_clipboard(
self, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a clipboard and returns a DataFrame.
Args:
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_clipboard(*args, **kwargs)
@check_suffix([".html"])
def read_html(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads an HTML file and returns a DataFrame.
Args:
file_path (str): The path to the HTML file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_html(file_path, *args, **kwargs)
@check_suffix([".feather"])
def read_feather(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a Feather file and returns a DataFrame.
Args:
file_path (str): The path to the Feather file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_feather(file_path, *args, **kwargs)
@check_suffix([".dta"])
def read_stata(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a Stata file and returns a DataFrame.
Args:
file_path (str): The path to the Stata file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_stata(file_path, *args, **kwargs)
@check_suffix([".sas"])
def read_sas(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a SAS file and returns a DataFrame.
Args:
file_path (str): The path to the SAS file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_sas(file_path, *args, **kwargs)
@check_suffix([".pkl"])
def read_pickle(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads a Pickle file and returns a DataFrame.
Args:
file_path (str): The path to the Pickle file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_pickle(file_path, *args, **kwargs)
@check_suffix([".h5"])
def read_hdf(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads an HDF file and returns a DataFrame.
Args:
file_path (str): The path to the HDF file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_hdf(file_path, *args, **kwargs)
@check_suffix([".orc"])
def read_orc(
self, file_path: str, *args: Any, **kwargs: Dict[str, Any]
) -> "DataFrame":
r"""Reads an ORC file and returns a DataFrame.
Args:
file_path (str): The path to the ORC file.
*args (Any): Additional positional arguments.
**kwargs (Dict[str, Any]): Additional keyword arguments.
Returns:
DataFrame: The DataFrame object.
"""
return pd.read_orc(file_path, *args, **kwargs)
|