File size: 3,465 Bytes
ed07e8e |
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 |
# analysis.py
import json
import pandas as pd
from collections import defaultdict
from typing import List, Dict
from datetime import datetime
class LogAnalyzer:
def __init__(self, log_path: str = "chat_history/chat_logs.json"):
self.log_path = log_path
self.logs = self._load_logs()
def _load_logs(self) -> List[Dict]:
"""Load and parse log entries from JSON file"""
try:
with open(self.log_path, "r", encoding="utf-8") as f:
return [json.loads(line) for line in f]
except (FileNotFoundError, json.JSONDecodeError):
return []
def get_basic_stats(self) -> Dict:
"""Calculate basic conversation statistics"""
if not self.logs:
return {}
return {
"total_interactions": len(self.logs),
"unique_users": len({log.get('session_id') for log in self.logs}),
"avg_response_length": pd.Series([len(log['bot_response']) for log in self.logs]).mean(),
"most_common_questions": self._get_common_questions(),
"knowledge_base_usage": self._calculate_kb_usage()
}
def _get_common_questions(self, top_n: int = 5) -> List[Dict]:
"""Identify most frequent user questions"""
question_counts = defaultdict(int)
for log in self.logs:
question_counts[log['user_input']] += 1
return sorted(
[{"question": k, "count": v} for k, v in question_counts.items()],
key=lambda x: x["count"],
reverse=True
)[:top_n]
def _calculate_kb_usage(self) -> Dict:
"""Analyze knowledge base effectiveness"""
context_usage = defaultdict(int)
for log in self.logs:
if log.get('context'):
context_usage['with_context'] += 1
else:
context_usage['without_context'] += 1
return context_usage
def temporal_analysis(self) -> Dict:
"""Analyze usage patterns over time"""
df = pd.DataFrame(self.logs)
df['timestamp'] = pd.to_datetime(df['timestamp'])
return {
"daily_activity": df.resample('D', on='timestamp').size().to_dict(),
"hourly_pattern": df.groupby(df['timestamp'].dt.hour).size().to_dict()
}
def generate_report(self) -> str:
"""Generate comprehensive analysis report"""
stats = self.get_basic_stats()
temporal = self.temporal_analysis()
report = f"""
Legal Assistant Usage Report
----------------------------
Period: {self.logs[0]['timestamp']} - {self.logs[-1]['timestamp']}
Total Interactions: {stats['total_interactions']}
Unique Users: {stats['unique_users']}
Average Response Length: {stats['avg_response_length']:.1f} chars
Top Questions:
{''.join(f"{q['question']}: {q['count']}\n" for q in stats['most_common_questions'])}
Knowledge Base Usage:
- With context: {stats['knowledge_base_usage'].get('with_context', 0)}
- Without context: {stats['knowledge_base_usage'].get('without_context', 0)}
Usage Patterns:
- Daily Activity: {temporal['daily_activity']}
- Hourly Distribution: {temporal['hourly_pattern']}
"""
return report |