Spaces:
Runtime error
Runtime error
File size: 6,019 Bytes
c69ba8c |
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 |
#!/usr/bin/env python3
"""
Fixed SmoLagent Data Analysis - Working Version
"""
import pandas as pd
from smolagents import CodeAgent, DuckDuckGoSearchTool
import warnings
warnings.filterwarnings('ignore')
# Your CSV file path
csv_file_path = "C:/Users/Cosmo/Desktop/NTU Peak Singtel/outsystems_sample_logs_6months.csv"
class FixedDataExplorer:
"""Working SmoLagent data explorer"""
def __init__(self, csv_path=csv_file_path):
self.csv_path = csv_path
self.df = None
self.agent = None
self.load_data()
self.setup_agent()
def load_data(self):
"""Load the CSV data"""
try:
self.df = pd.read_csv(self.csv_path)
print(f"✅ Data loaded: {self.df.shape[0]} rows, {self.df.shape[1]} columns")
return True
except Exception as e:
print(f"❌ Data loading failed: {e}")
return False
def setup_agent(self):
"""Setup SmoLagent with proper model"""
try:
print("🤖 Setting up SmoLagent...")
# Option 1: Try Ollama (if running locally)
try:
from smolagents import OllamaModel
model = OllamaModel(model_id="llama2")
self.agent = CodeAgent(
tools=[DuckDuckGoSearchTool()],
model=model
)
print("✅ SmoLagent configured with Ollama")
return
except:
pass
# Option 2: Use OpenAI (requires API key)
try:
from smolagents import OpenAIModel
import os
if os.getenv('OPENAI_API_KEY'):
model = OpenAIModel(model_id="gpt-3.5-turbo")
self.agent = CodeAgent(
tools=[DuckDuckGoSearchTool()],
model=model
)
print("✅ SmoLagent configured with OpenAI")
return
except:
pass
# Option 3: Use smaller HuggingFace model (lighter download)
try:
from smolagents import TransformersModel
model = TransformersModel(model_id="microsoft/DialoGPT-small") # Smaller model
self.agent = CodeAgent(
tools=[DuckDuckGoSearchTool()],
model=model
)
print("✅ SmoLagent configured with small Transformers model")
return
except Exception as e:
print(f"❌ Model setup failed: {e}")
print("❌ No AI model could be configured")
print("💡 You can still use basic data analysis features")
except Exception as e:
print(f"❌ Agent setup failed: {e}")
def basic_analysis(self):
"""Run basic data analysis without AI"""
if self.df is None:
print("❌ No data loaded")
return
print("\n📊 BASIC DATA ANALYSIS")
print("=" * 40)
# Basic stats
print(f"📋 Dataset: {self.df.shape[0]} rows, {self.df.shape[1]} columns")
print(f"📋 Columns: {list(self.df.columns)}")
# Log level analysis
if 'LogLevel' in self.df.columns:
log_counts = self.df['LogLevel'].value_counts()
print(f"\n📈 Log Level Distribution:")
for level, count in log_counts.items():
pct = count / len(self.df) * 100
print(f" {level}: {count} ({pct:.1f}%)")
# Error analysis
if 'LogLevel' in self.df.columns:
errors = self.df[self.df['LogLevel'] == 'Error']
if not errors.empty and 'Module' in errors.columns:
print(f"\n🚨 Top Error Modules:")
top_errors = errors['Module'].value_counts().head(3)
for module, count in top_errors.items():
print(f" • {module}: {count} errors")
# Missing data
missing = self.df.isnull().sum()
print(f"\n❌ Missing Data:")
for col, count in missing.items():
if count > 0:
pct = count / len(self.df) * 100
print(f" • {col}: {count} ({pct:.1f}%)")
def ai_analysis(self, query):
"""Run AI-powered analysis"""
if self.agent is None:
print("❌ AI agent not available. Please configure a model first.")
return
if self.df is None:
print("❌ No data loaded")
return
try:
# Prepare data context for AI
data_summary = f"""
Dataset: {self.df.shape[0]} rows, {self.df.shape[1]} columns
Columns: {list(self.df.columns)}
Sample data: {self.df.head(2).to_string()}
"""
full_query = f"""
Analyze this OutSystems log data:
{data_summary}
User question: {query}
"""
print(f"🤖 AI analyzing: {query}")
response = self.agent.run(full_query)
print(f"🤖 AI Response: {response}")
except Exception as e:
print(f"❌ AI analysis failed: {e}")
def main():
"""Main function"""
print("🚀 FIXED SMOLAGENT DATA ANALYZER")
print("=" * 50)
# Create explorer
explorer = FixedDataExplorer()
# Run basic analysis
explorer.basic_analysis()
# Test AI if available
if explorer.agent:
print(f"\n🤖 AI FEATURES AVAILABLE!")
print(" Try: explorer.ai_analysis('What are the main error types?')")
else:
print(f"\n💡 AI features not available - need model configuration")
return explorer
if __name__ == "__main__":
explorer = main()
|