Function load_data

webui/app.py:342–402

Load data file

()

@app.route('/api/load-data', methods=['POST'])
def load_data():
    """Load data file"""
    try:
        data = request.get_json()
        file_path = data.get('file_path')
        
        if not file_path:
            return jsonify({'error': 'File path cannot be empty'}), 400
        
        df, error = load_data_file(file_path)
        if error:
            return jsonify({'error': error}), 400
        
        # Detect data time frequency
        def detect_timeframe(df):
            if len(df) < 2:
                return "Unknown"
            
            time_diffs = []
            for i in range(1, min(10, len(df))):  # Check first 10 time differences
                diff = df['timestamps'].iloc[i] - df['timestamps'].iloc[i-1]
                time_diffs.append(diff)
            
            if not time_diffs:
                return "Unknown"
            
            # Calculate average time difference
            avg_diff = sum(time_diffs, pd.Timedelta(0)) / len(time_diffs)
            
            # Convert to readable format
            if avg_diff < pd.Timedelta(minutes=1):
                return f"{avg_diff.total_seconds():.0f} seconds"
            elif avg_diff < pd.Timedelta(hours=1):
                return f"{avg_diff.total_seconds() / 60:.0f} minutes"
            elif avg_diff < pd.Timedelta(days=1):
                return f"{avg_diff.total_seconds() / 3600:.0f} hours"
            else:
                return f"{avg_diff.days} days"
        
        # Return data information
        data_info = {
            'rows': len(df),
            'columns': list(df.columns),
            'start_date': df['timestamps'].min().isoformat() if 'timestamps' in df.columns else 'N/A',
            'end_date': df['timestamps'].max().isoformat() if 'timestamps' in df.columns else 'N/A',
            'price_range': {
                'min': float(df[['open', 'high', 'low', 'close']].min().min()),
                'max': float(df[['open', 'high', 'low', 'close']].max().max())
            },
            'prediction_columns': ['open', 'high', 'low', 'close'] + (['volume'] if 'volume' in df.columns else []),
            'timeframe': detect_timeframe(df)
        }
        
        return jsonify({
            'success': True,
            'data_info': data_info,
            'message': f'Successfully loaded data, total {len(df)} rows'
        })