File size: 1,278 Bytes
e5bc014 |
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 |
#!/usr/bin/env python3
"""Statistical Analysis Plugin"""
import pandas as pd
from typing import Dict, Any
class StatisticalAnalyzer:
"""Perform statistical analysis on data."""
def analyze(self, df: pd.DataFrame) -> Dict[str, Any]:
"""Generate comprehensive statistical summary."""
analysis = {"shape": {"rows": len(df), "columns": len(df.columns)}, "columns": {}}
for col in df.columns:
col_analysis = {"name": col, "dtype": str(df[col].dtype)}
col_analysis["missing_percent"] = float(df[col].isna().mean() * 100)
if pd.api.types.is_numeric_dtype(df[col]):
col_analysis.update({
"mean": float(df[col].mean()),
"std": float(df[col].std()),
"min": float(df[col].min()),
"max": float(df[col].max()),
"median": float(df[col].median())
})
elif pd.api.types.is_datetime64_any_dtype(df[col]):
col_analysis.update({"min_date": str(df[col].min()), "max_date": str(df[col].max())})
else:
col_analysis.update({"unique_values": int(df[col].nunique())})
analysis["columns"][col] = col_analysis
return analysis
|