| 1 | #!/usr/bin/env python3 |
| 2 | """ |
| 3 | Data processing utilities |
| 4 | """ |
| 5 | |
| 6 | import numpy as np |
| 7 | import pandas as pd |
| 8 | |
| 9 | <<<<<<< HEAD |
| 10 | def load_data(filename, use_cache=True): |
| 11 | """Load data from file with optional caching""" |
| 12 | if use_cache: |
| 13 | # Try to load from cache |
| 14 | cache_file = filename + '.cache' |
| 15 | if os.path.exists(cache_file): |
| 16 | return pd.read_pickle(cache_file) |
| 17 | |
| 18 | # Load from original file |
| 19 | data = pd.read_csv(filename) |
| 20 | |
| 21 | if use_cache: |
| 22 | data.to_pickle(cache_file) |
| 23 | |
| 24 | return data |
| 25 | ======= |
| 26 | def load_data(filename): |
| 27 | """Load data from CSV file""" |
| 28 | return pd.read_csv(filename, parse_dates=True, index_col=0) |
| 29 | >>>>>>> feature-simple-loader |
| 30 | |
| 31 | class DataProcessor: |
| 32 | def __init__(self, data): |
| 33 | self.data = data |
| 34 | self.processed = False |
| 35 | |
| 36 | <<<<<<< HEAD |
| 37 | def normalize(self, method='minmax'): |
| 38 | """Normalize data using specified method""" |
| 39 | if method == 'minmax': |
| 40 | # Min-max normalization |
| 41 | self.data = (self.data - self.data.min()) / (self.data.max() - self.data.min()) |
| 42 | elif method == 'zscore': |
| 43 | # Z-score normalization |
| 44 | self.data = (self.data - self.data.mean()) / self.data.std() |
| 45 | else: |
| 46 | raise ValueError(f"Unknown normalization method: {method}") |
| 47 | |
| 48 | self.processed = True |
| 49 | ======= |
| 50 | def normalize(self): |
| 51 | """Normalize data using z-score""" |
| 52 | self.data = (self.data - self.data.mean()) / self.data.std() |
| 53 | self.processed = True |
| 54 | >>>>>>> feature-zscore-only |
| 55 | |
| 56 | def save(self, filename): |
| 57 | """Save processed data""" |
| 58 | self.data.to_csv(filename, index=False) |
| 59 | |
| 60 | if __name__ == "__main__": |
| 61 | data = load_data("input.csv") |
| 62 | processor = DataProcessor(data) |
| 63 | processor.normalize() |
| 64 | processor.save("output.csv") |