File size: 12,283 Bytes
31d3380
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# import pandas as pd
# import numpy as np
# from PIL import Image
# from pathlib import Path
# from typing import List, Dict, Any, Union, Tuple, Optional
# import os
# import json


# class DataLoader:
#     def __init__(self):
#         self.supported_image_formats = ['.jpg', '.jpeg', '.png', '.bmp', '.gif', '.webp']
#         self.supported_text_formats = ['.txt', '.csv', '.json', '.xlsx', '.xls']

#     def load_csv(self, file_path: Union[str, Path]) -> pd.DataFrame:
#         return pd.read_csv(file_path)

#     def load_excel(self, file_path: Union[str, Path], sheet_name: Union[str, int] = 0) -> pd.DataFrame:
#         return pd.read_excel(file_path, sheet_name=sheet_name)

#     def load_json(self, file_path: Union[str, Path]) -> pd.DataFrame:
#         return pd.read_json(file_path)

#     def load_image(self, file_path: Union[str, Path]) -> Image.Image:
#         return Image.open(file_path).convert('RGB')

#     def load_images_from_folder(self, folder_path: Union[str, Path]) -> List[Tuple[str, Image.Image]]:
#         folder = Path(folder_path)
#         images = []
#         for ext in self.supported_image_formats:
#             for file_path in folder.glob(f"*{ext}"):
#                 try:
#                     img = Image.open(file_path).convert('RGB')
#                     images.append((str(file_path), img))
#                 except Exception as e:
#                     print(f"Error loading {file_path}: {e}")
#         return images

#     def load_text_file(self, file_path: Union[str, Path]) -> str:
#         with open(file_path, 'r', encoding='utf-8') as f:
#             return f.read()

#     def detect_file_type(self, file_path: Union[str, Path]) -> str:
#         path = Path(file_path)
#         suffix = path.suffix.lower()
#         if suffix in self.supported_image_formats:
#             return "image"
#         elif suffix == '.csv':
#             return "csv"
#         elif suffix in ['.xlsx', '.xls']:
#             return "excel"
#         elif suffix == '.json':
#             return "json"
#         elif suffix == '.txt':
#             return "text"
#         else:
#             return "unknown"

#     def auto_load(self, file_path: Union[str, Path]) -> Tuple[Any, str]:
#         file_type = self.detect_file_type(file_path)
#         if file_type == "csv":
#             return self.load_csv(file_path), "dataframe"
#         elif file_type == "excel":
#             return self.load_excel(file_path), "dataframe"
#         elif file_type == "json":
#             return self.load_json(file_path), "dataframe"
#         elif file_type == "image":
#             return self.load_image(file_path), "image"
#         elif file_type == "text":
#             return self.load_text_file(file_path), "text"
#         else:
#             raise ValueError(f"Unsupported file type: {file_type}")

#     def get_data_summary(self, df: pd.DataFrame) -> Dict[str, Any]:
#         summary = {
#             "row_count": int(len(df)),
#             "columns": df.columns.tolist(),
#             "features": int(len(df.columns)),
#             "dtypes": df.dtypes.astype(str).to_dict(),
#             "missing_values": df.isnull().sum().to_dict(),
#             "missing_percent": (df.isnull().sum() / len(df) * 100).round(2).to_dict(),
#             "numeric_columns": df.select_dtypes(include=[np.number]).columns.tolist(),
#             "categorical_columns": df.select_dtypes(include=['object', 'category']).columns.tolist(),
#             "duplicate_rows": int(df.duplicated().sum()),
#         }

#         numeric_df = df.select_dtypes(include=[np.number])
#         if not numeric_df.empty:
#             summary["numeric_summary"] = {
#                 "mean": numeric_df.mean().round(4).to_dict(),
#                 "std": numeric_df.std().round(4).to_dict(),
#                 "min": numeric_df.min().to_dict(),
#                 "max": numeric_df.max().to_dict(),
#                 "median": numeric_df.median().to_dict(),
#             }

#         return summary

#     def preprocess_dataframe(
#         self,
#         df: pd.DataFrame,
#         drop_non_numeric: bool = True,
#         fill_strategy: str = "median"
#     ) -> pd.DataFrame:
#         df = df.copy()

#         df = df.dropna(axis=1, how='all')

#         for col in df.columns:
#             if df[col].dtype == 'object':
#                 try:
#                     df[col] = pd.to_numeric(df[col])
#                 except (ValueError, TypeError):
#                     if drop_non_numeric:
#                         df = df.drop(columns=[col])
#                     else:
#                         df = pd.get_dummies(df, columns=[col], drop_first=True)

#         for col in df.columns:
#             if df[col].isnull().any():
#                 if df[col].dtype in ['int64', 'float64', 'int32', 'float32']:
#                     if fill_strategy == "median":
#                         df[col] = df[col].fillna(df[col].median())
#                     elif fill_strategy == "mean":
#                         df[col] = df[col].fillna(df[col].mean())
#                     else:
#                         df[col] = df[col].fillna(0)
#                 elif df[col].dtype == 'bool':
#                     df[col] = df[col].fillna(False)
#                 else:
#                     mode_val = df[col].mode()
#                     df[col] = df[col].fillna(mode_val.iloc[0] if not mode_val.empty else "unknown")

#         return df

#     def split_features_target(
#         self, df: pd.DataFrame, target_column: str
#     ) -> Tuple[pd.DataFrame, pd.Series]:
#         if target_column not in df.columns:
#             raise ValueError(f"Target column '{target_column}' not found in dataframe")
#         X = df.drop(columns=[target_column])
#         y = df[target_column]
#         return X, y

#     def get_class_distribution(self, series: pd.Series) -> Dict[str, int]:
#         return series.value_counts().to_dict()

#     def detect_task_type(self, series: pd.Series) -> str:
#         """Auto-detect whether classification or regression is appropriate."""
#         if series.dtype == 'object' or series.nunique() <= 20:
#             return "classification"
#         return "regression"



import pandas as pd
import numpy as np
from PIL import Image
from pathlib import Path
from typing import List, Dict, Any, Union, Tuple, Optional
import os
import json


class DataLoader:
    def __init__(self):
        self.supported_image_formats = ['.jpg', '.jpeg', '.png', '.bmp', '.gif', '.webp']
        self.supported_text_formats = ['.txt', '.csv', '.json', '.xlsx', '.xls']

    def load_csv(self, file_path: Union[str, Path]) -> pd.DataFrame:
        return pd.read_csv(file_path)

    def load_excel(self, file_path: Union[str, Path], sheet_name: Union[str, int] = 0) -> pd.DataFrame:
        return pd.read_excel(file_path, sheet_name=sheet_name)

    def load_json(self, file_path: Union[str, Path]) -> pd.DataFrame:
        return pd.read_json(file_path)

    def load_image(self, file_path: Union[str, Path]) -> Image.Image:
        return Image.open(file_path).convert('RGB')

    def load_images_from_folder(self, folder_path: Union[str, Path]) -> List[Tuple[str, Image.Image]]:
        folder = Path(folder_path)
        images = []
        for ext in self.supported_image_formats:
            for file_path in folder.glob(f"*{ext}"):
                try:
                    img = Image.open(file_path).convert('RGB')
                    images.append((str(file_path), img))
                except Exception as e:
                    print(f"Error loading {file_path}: {e}")
        return images

    def load_text_file(self, file_path: Union[str, Path]) -> str:
        with open(file_path, 'r', encoding='utf-8') as f:
            return f.read()

    def detect_file_type(self, file_path: Union[str, Path]) -> str:
        path = Path(file_path)
        suffix = path.suffix.lower()
        if suffix in self.supported_image_formats:
            return "image"
        elif suffix == '.csv':
            return "csv"
        elif suffix in ['.xlsx', '.xls']:
            return "excel"
        elif suffix == '.json':
            return "json"
        elif suffix == '.txt':
            return "text"
        else:
            return "unknown"

    def auto_load(self, file_path: Union[str, Path]) -> Tuple[Any, str]:
        file_type = self.detect_file_type(file_path)
        if file_type == "csv":
            return self.load_csv(file_path), "dataframe"
        elif file_type == "excel":
            return self.load_excel(file_path), "dataframe"
        elif file_type == "json":
            return self.load_json(file_path), "dataframe"
        elif file_type == "image":
            return self.load_image(file_path), "image"
        elif file_type == "text":
            return self.load_text_file(file_path), "text"
        else:
            raise ValueError(f"Unsupported file type: {file_type}")

    def get_data_summary(self, df: pd.DataFrame) -> Dict[str, Any]:
        summary = {
            "row_count": int(len(df)),
            "columns": df.columns.tolist(),
            "features": int(len(df.columns)),
            "dtypes": df.dtypes.astype(str).to_dict(),
            "missing_values": df.isnull().sum().to_dict(),
            "missing_percent": (df.isnull().sum() / len(df) * 100).round(2).to_dict(),
            "numeric_columns": df.select_dtypes(include=[np.number]).columns.tolist(),
            "categorical_columns": df.select_dtypes(include=['object', 'category']).columns.tolist(),
            "duplicate_rows": int(df.duplicated().sum()),
        }

        numeric_df = df.select_dtypes(include=[np.number])
        if not numeric_df.empty:
            summary["numeric_summary"] = {
                "mean": numeric_df.mean().round(4).to_dict(),
                "std": numeric_df.std().round(4).to_dict(),
                "min": numeric_df.min().to_dict(),
                "max": numeric_df.max().to_dict(),
                "median": numeric_df.median().to_dict(),
            }

        return summary

    def preprocess_dataframe(
        self,
        df: pd.DataFrame,
        drop_non_numeric: bool = True,
        fill_strategy: str = "median"
    ) -> pd.DataFrame:
        df = df.copy()

        # Drop fully empty columns
        df = df.dropna(axis=1, how='all')

        for col in df.columns:
            if df[col].dtype == 'object':
                try:
                    df[col] = pd.to_numeric(df[col])
                except (ValueError, TypeError):
                    if drop_non_numeric:
                        df = df.drop(columns=[col])
                    else:
                        df = pd.get_dummies(df, columns=[col], drop_first=True)

        # Fill missing values
        for col in df.columns:
            if df[col].isnull().any():
                if df[col].dtype in ['int64', 'float64', 'int32', 'float32']:
                    if fill_strategy == "median":
                        df[col] = df[col].fillna(df[col].median())
                    elif fill_strategy == "mean":
                        df[col] = df[col].fillna(df[col].mean())
                    else:
                        df[col] = df[col].fillna(0)
                elif df[col].dtype == 'bool':
                    df[col] = df[col].fillna(False)
                else:
                    mode_val = df[col].mode()
                    df[col] = df[col].fillna(mode_val.iloc[0] if not mode_val.empty else "unknown")

        return df

    def split_features_target(
        self, df: pd.DataFrame, target_column: str
    ) -> Tuple[pd.DataFrame, pd.Series]:
        if target_column not in df.columns:
            raise ValueError(f"Target column '{target_column}' not found in dataframe")
        X = df.drop(columns=[target_column])
        y = df[target_column]
        return X, y

    def get_class_distribution(self, series: pd.Series) -> Dict[str, int]:
        return series.value_counts().to_dict()

    def detect_task_type(self, series: pd.Series) -> str:
        """Auto-detect whether classification or regression is appropriate."""
        if series.dtype == 'object' or series.nunique() <= 20:
            return "classification"
        return "regression"