File size: 9,242 Bytes
e478478
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Sample Data Generator - InsightGenAI
====================================
Generate sample datasets for testing the application.

Author: InsightGenAI Team
Version: 1.0.0
"""

import pandas as pd
import numpy as np
from typing import Optional
import argparse


def generate_classification_dataset(n_samples: int = 1000, 
                                    n_features: int = 10,
                                    n_classes: int = 2,
                                    noise: float = 0.1,
                                    output_path: Optional[str] = None) -> pd.DataFrame:
    """
    Generate a synthetic classification dataset.
    
    Args:
        n_samples: Number of samples
        n_features: Number of features
        n_classes: Number of classes
        noise: Noise level
        output_path: Path to save CSV (optional)
        
    Returns:
        pd.DataFrame: Generated dataset
    """
    np.random.seed(42)
    
    # Generate features
    data = {}
    for i in range(n_features):
        if i < n_features // 2:
            data[f'feature_{i}'] = np.random.randn(n_samples)
        else:
            data[f'feature_{i}'] = np.random.randint(0, 100, n_samples)
    
    # Generate target with some relationship to features
    X = np.column_stack([data[f'feature_{i}'] for i in range(min(3, n_features))])
    weights = np.random.randn(X.shape[1])
    logits = X @ weights + np.random.randn(n_samples) * noise
    
    if n_classes == 2:
        target = (logits > np.median(logits)).astype(int)
    else:
        target = pd.cut(logits, bins=n_classes, labels=range(n_classes)).astype(int)
    
    data['target'] = target
    
    # Add some categorical features
    data['category'] = np.random.choice(['A', 'B', 'C'], n_samples)
    data['region'] = np.random.choice(['North', 'South', 'East', 'West'], n_samples)
    
    # Add a text column
    text_templates = [
        "Customer reported satisfaction with the product.",
        "User experienced issues with the interface.",
        "Positive feedback received from client.",
        "Technical difficulties encountered during usage.",
        "Excellent performance and reliability noted."
    ]
    data['feedback'] = np.random.choice(text_templates, n_samples)
    
    # Add missing values (5% random)
    df = pd.DataFrame(data)
    mask = np.random.random(df.shape) < 0.05
    df = df.mask(mask)
    
    if output_path:
        df.to_csv(output_path, index=False)
        print(f"Classification dataset saved to {output_path}")
    
    return df


def generate_regression_dataset(n_samples: int = 1000,
                                n_features: int = 8,
                                noise: float = 0.5,
                                output_path: Optional[str] = None) -> pd.DataFrame:
    """
    Generate a synthetic regression dataset.
    
    Args:
        n_samples: Number of samples
        n_features: Number of features
        noise: Noise level
        output_path: Path to save CSV (optional)
        
    Returns:
        pd.DataFrame: Generated dataset
    """
    np.random.seed(42)
    
    # Generate features
    data = {}
    for i in range(n_features):
        if i < n_features // 2:
            data[f'feature_{i}'] = np.random.randn(n_samples)
        else:
            data[f'feature_{i}'] = np.random.randint(1, 100, n_samples)
    
    # Generate target with linear relationship
    X = np.column_stack([data[f'feature_{i}'] for i in range(n_features)])
    weights = np.random.randn(n_features)
    target = X @ weights + np.random.randn(n_samples) * noise
    
    data['target'] = target
    
    # Add categorical features
    data['category'] = np.random.choice(['Type1', 'Type2', 'Type3'], n_samples)
    
    # Add datetime column
    data['date'] = pd.date_range(start='2020-01-01', periods=n_samples, freq='D')
    
    df = pd.DataFrame(data)
    
    if output_path:
        df.to_csv(output_path, index=False)
        print(f"Regression dataset saved to {output_path}")
    
    return df


def generate_customer_churn_dataset(n_samples: int = 2000,
                                     output_path: Optional[str] = None) -> pd.DataFrame:
    """
    Generate a customer churn prediction dataset.
    
    Args:
        n_samples: Number of samples
        output_path: Path to save CSV (optional)
        
    Returns:
        pd.DataFrame: Generated dataset
    """
    np.random.seed(42)
    
    data = {
        'customer_id': range(1, n_samples + 1),
        'age': np.random.randint(18, 80, n_samples),
        'gender': np.random.choice(['Male', 'Female'], n_samples),
        'tenure': np.random.randint(0, 72, n_samples),
        'monthly_charges': np.random.uniform(20, 120, n_samples),
        'total_charges': np.random.uniform(100, 8000, n_samples),
        'contract': np.random.choice(['Month-to-month', 'One year', 'Two year'], n_samples),
        'payment_method': np.random.choice(['Electronic check', 'Mailed check', 
                                           'Bank transfer', 'Credit card'], n_samples),
        'internet_service': np.random.choice(['DSL', 'Fiber optic', 'No'], n_samples),
        'tech_support': np.random.choice(['Yes', 'No'], n_samples),
        'online_security': np.random.choice(['Yes', 'No'], n_samples),
        'paperless_billing': np.random.choice(['Yes', 'No'], n_samples),
    }
    
    # Generate churn based on features
    churn_prob = (
        0.3 + 
        (data['tenure'] < 12) * 0.2 +
        (data['contract'] == 'Month-to-month') * 0.15 +
        (data['payment_method'] == 'Electronic check') * 0.1 +
        (data['tech_support'] == 'No') * 0.1 +
        np.random.randn(n_samples) * 0.1
    )
    churn_prob = np.clip(churn_prob, 0, 1)
    data['churn'] = (np.random.random(n_samples) < churn_prob).astype(int)
    
    df = pd.DataFrame(data)
    
    if output_path:
        df.to_csv(output_path, index=False)
        print(f"Customer churn dataset saved to {output_path}")
    
    return df


def generate_housing_dataset(n_samples: int = 1500,
                              output_path: Optional[str] = None) -> pd.DataFrame:
    """
    Generate a housing price prediction dataset.
    
    Args:
        n_samples: Number of samples
        output_path: Path to save CSV (optional)
        
    Returns:
        pd.DataFrame: Generated dataset
    """
    np.random.seed(42)
    
    data = {
        'sqft_living': np.random.randint(500, 5000, n_samples),
        'sqft_lot': np.random.randint(1000, 50000, n_samples),
        'bedrooms': np.random.randint(1, 6, n_samples),
        'bathrooms': np.random.randint(1, 5, n_samples),
        'floors': np.random.randint(1, 4, n_samples),
        'waterfront': np.random.choice([0, 1], n_samples, p=[0.95, 0.05]),
        'view': np.random.randint(0, 5, n_samples),
        'condition': np.random.randint(1, 6, n_samples),
        'grade': np.random.randint(1, 14, n_samples),
        'yr_built': np.random.randint(1900, 2024, n_samples),
        'yr_renovated': np.random.choice([0] + list(range(1950, 2024)), n_samples),
        'zipcode': np.random.choice([98101, 98102, 98103, 98104, 98105, 
                                     98106, 98107, 98108, 98109, 98112], n_samples),
    }
    
    # Generate price based on features
    base_price = 50000
    price = (
        base_price +
        data['sqft_living'] * 200 +
        data['sqft_lot'] * 2 +
        data['bedrooms'] * 25000 +
        data['bathrooms'] * 35000 +
        data['waterfront'] * 500000 +
        data['view'] * 50000 +
        data['grade'] * 20000 +
        (2024 - np.array(data['yr_built'])) * (-1000) +
        np.random.randn(n_samples) * 50000
    )
    
    data['price'] = np.maximum(price, 50000).astype(int)
    
    df = pd.DataFrame(data)
    
    if output_path:
        df.to_csv(output_path, index=False)
        print(f"Housing dataset saved to {output_path}")
    
    return df


def main():
    """Main function for CLI usage."""
    parser = argparse.ArgumentParser(
        description='Generate sample datasets for InsightGenAI testing'
    )
    parser.add_argument(
        'dataset_type',
        choices=['classification', 'regression', 'churn', 'housing'],
        help='Type of dataset to generate'
    )
    parser.add_argument(
        '-n', '--samples',
        type=int,
        default=1000,
        help='Number of samples (default: 1000)'
    )
    parser.add_argument(
        '-o', '--output',
        type=str,
        default=None,
        help='Output file path'
    )
    
    args = parser.parse_args()
    
    if args.output is None:
        args.output = f'sample_{args.dataset_type}_data.csv'
    
    if args.dataset_type == 'classification':
        generate_classification_dataset(n_samples=args.samples, output_path=args.output)
    elif args.dataset_type == 'regression':
        generate_regression_dataset(n_samples=args.samples, output_path=args.output)
    elif args.dataset_type == 'churn':
        generate_customer_churn_dataset(n_samples=args.samples, output_path=args.output)
    elif args.dataset_type == 'housing':
        generate_housing_dataset(n_samples=args.samples, output_path=args.output)


if __name__ == "__main__":
    main()