Spaces:
Sleeping
Sleeping
File size: 10,464 Bytes
923b896 fed116a 923b896 fed116a 923b896 fed116a 923b896 fed116a 923b896 fed116a 923b896 fed116a 923b896 fed116a 923b896 fed116a 923b896 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 |
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
def load_and_preprocess_data(file_path):
# Read Excel file, skipping the first 2 rows
df = pd.read_excel(file_path, skiprows=2)
# Extract data for each configuration using column letters
milvus_llama = df.iloc[:, 2:8].copy() # Columns C to H
milvus_llama.columns = ['RMSE_Context_Rel', 'RMSE_Context_Util', 'AUCROC',
'Retrieval_Time', 'Context_Relevance', 'Context_Utilization']
weaviate_mistral = df.iloc[:, 9:16].copy() # Columns J to P
weaviate_mistral.columns = ['Retrieval_Time', 'Context_Rel', 'Util',
'Adherence', 'RMSE_Context_Rel', 'RMSE_Context_Util', 'AUCROC']
milvus_mistral = df.iloc[:, 17:24].copy() # Columns R to X
milvus_mistral.columns = ['Retrieval_Time', 'Context_Rel', 'Util',
'Adherence', 'RMSE_Context_Rel', 'RMSE_Context_Util', 'AUCROC']
# Replace 'na' with NaN and convert to float
milvus_llama = milvus_llama.replace('na', np.nan).astype(float)
weaviate_mistral = weaviate_mistral.replace('na', np.nan).astype(float)
milvus_mistral = milvus_mistral.replace('na', np.nan).astype(float)
return milvus_llama, weaviate_mistral, milvus_mistral
def create_performance_comparison(milvus_llama, weaviate_mistral, milvus_mistral):
plt.style.use('default') # Using default style instead of seaborn
fig, axes = plt.subplots(2, 2, figsize=(15, 12))
# Retrieval Time Comparison
data = {
'Milvus + LLaMA': milvus_llama['Retrieval_Time'].dropna(),
'Weaviate + Mistral': weaviate_mistral['Retrieval_Time'].dropna(),
'Milvus + Mistral': milvus_mistral['Retrieval_Time'].dropna()
}
sns.boxplot(data=pd.DataFrame(data), ax=axes[0,0])
axes[0,0].set_title('VectorDB Retrieval Time Comparison')
axes[0,0].set_ylabel('Time (seconds)')
axes[0,0].tick_params(axis='x', rotation=45)
# RMSE Context Relevance Comparison
data = {
'Milvus + LLaMA': milvus_llama['RMSE_Context_Rel'].dropna(),
'Weaviate + Mistral': weaviate_mistral['RMSE_Context_Rel'].dropna(),
'Milvus + Mistral': milvus_mistral['RMSE_Context_Rel'].dropna()
}
sns.boxplot(data=pd.DataFrame(data), ax=axes[0,1])
axes[0,1].set_title('RMSE Context Relevance')
axes[0,1].tick_params(axis='x', rotation=45)
# RMSE Context Utilization Comparison
data = {
'Milvus + LLaMA': milvus_llama['RMSE_Context_Util'].dropna(),
'Weaviate + Mistral': weaviate_mistral['RMSE_Context_Util'].dropna(),
'Milvus + Mistral': milvus_mistral['RMSE_Context_Util'].dropna()
}
sns.boxplot(data=pd.DataFrame(data), ax=axes[1,0])
axes[1,0].set_title('RMSE Context Utilization')
axes[1,0].tick_params(axis='x', rotation=45)
# AUROC Comparison
data = {
'Milvus + LLaMA': milvus_llama['AUCROC'].dropna(),
'Weaviate + Mistral': weaviate_mistral['AUCROC'].dropna(),
'Milvus + Mistral': milvus_mistral['AUCROC'].dropna()
}
sns.boxplot(data=pd.DataFrame(data), ax=axes[1,1])
axes[1,1].set_title('AUROC Scores')
axes[1,1].tick_params(axis='x', rotation=45)
plt.tight_layout()
plt.savefig('report/visualizations/performance_comparison.png', dpi=300, bbox_inches='tight')
plt.close()
def create_correlation_plots(milvus_llama, weaviate_mistral, milvus_mistral):
# Create separate plots for each model
# 1. Milvus + LLaMA
plt.figure(figsize=(15, 10))
# Relevance comparison
plt.subplot(2, 1, 1)
plt.plot(range(len(milvus_llama)), milvus_llama['RMSE_Context_Rel'], 'o--',
color='red', label='RMSE Context Relevance', linewidth=2, alpha=0.7)
plt.plot(range(len(milvus_llama)), milvus_llama['Context_Relevance'], 'o-',
color='darkred', label='Context Relevance', linewidth=2, alpha=0.7)
plt.title('Milvus + LLaMA: Context Relevance vs RMSE')
plt.xlabel('Data Points')
plt.ylabel('Score')
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
# Utilization comparison
plt.subplot(2, 1, 2)
plt.plot(range(len(milvus_llama)), milvus_llama['RMSE_Context_Util'], 'o--',
color='blue', label='RMSE Context Utilization', linewidth=2, alpha=0.7)
plt.plot(range(len(milvus_llama)), milvus_llama['Context_Utilization'], 'o-',
color='darkblue', label='Context Utilization', linewidth=2, alpha=0.7)
plt.title('Milvus + LLaMA: Context Utilization vs RMSE')
plt.xlabel('Data Points')
plt.ylabel('Score')
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
plt.tight_layout()
plt.savefig('report/visualizations/milvus_llama_plots.png', bbox_inches='tight', dpi=300)
plt.close()
# 2. Weaviate + Mistral
plt.figure(figsize=(15, 10))
# Relevance comparison
plt.subplot(2, 1, 1)
plt.plot(range(len(weaviate_mistral)), weaviate_mistral['RMSE_Context_Rel'], 'o--',
color='red', label='RMSE Context Relevance', linewidth=2, alpha=0.7)
plt.plot(range(len(weaviate_mistral)), weaviate_mistral['Context_Rel'], 'o-',
color='darkred', label='Context Relevance', linewidth=2, alpha=0.7)
plt.title('Weaviate + Mistral: Context Relevance vs RMSE')
plt.xlabel('Data Points')
plt.ylabel('Score')
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
# Utilization comparison
plt.subplot(2, 1, 2)
plt.plot(range(len(weaviate_mistral)), weaviate_mistral['RMSE_Context_Util'], 'o--',
color='blue', label='RMSE Context Utilization', linewidth=2, alpha=0.7)
plt.plot(range(len(weaviate_mistral)), weaviate_mistral['Util'], 'o-',
color='darkblue', label='Context Utilization', linewidth=2, alpha=0.7)
plt.title('Weaviate + Mistral: Context Utilization vs RMSE')
plt.xlabel('Data Points')
plt.ylabel('Score')
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
plt.tight_layout()
plt.savefig('report/visualizations/weaviate_mistral_plots.png', bbox_inches='tight', dpi=300)
plt.close()
# 3. Milvus + Mistral
plt.figure(figsize=(15, 10))
# Relevance comparison
plt.subplot(2, 1, 1)
plt.plot(range(len(milvus_mistral)), milvus_mistral['RMSE_Context_Rel'], 'o--',
color='red', label='RMSE Context Relevance', linewidth=2, alpha=0.7)
plt.plot(range(len(milvus_mistral)), milvus_mistral['Context_Rel'], 'o-',
color='darkred', label='Context Relevance', linewidth=2, alpha=0.7)
plt.title('Milvus + Mistral: Context Relevance vs RMSE')
plt.xlabel('Data Points')
plt.ylabel('Score')
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
# Utilization comparison
plt.subplot(2, 1, 2)
plt.plot(range(len(milvus_mistral)), milvus_mistral['RMSE_Context_Util'], 'o--',
color='blue', label='RMSE Context Utilization', linewidth=2, alpha=0.7)
plt.plot(range(len(milvus_mistral)), milvus_mistral['Util'], 'o-',
color='darkblue', label='Context Utilization', linewidth=2, alpha=0.7)
plt.title('Milvus + Mistral: Context Utilization vs RMSE')
plt.xlabel('Data Points')
plt.ylabel('Score')
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
plt.tight_layout()
plt.savefig('report/visualizations/milvus_mistral_plots.png', bbox_inches='tight', dpi=300)
plt.close()
# Print statistical analysis for each model
print("\nStatistical Analysis:")
models = {
'Milvus + LLaMA': (milvus_llama['RMSE_Context_Rel'], milvus_llama['Context_Relevance'],
milvus_llama['RMSE_Context_Util'], milvus_llama['Context_Utilization']),
'Weaviate + Mistral': (weaviate_mistral['RMSE_Context_Rel'], weaviate_mistral['Context_Rel'],
weaviate_mistral['RMSE_Context_Util'], weaviate_mistral['Util']),
'Milvus + Mistral': (milvus_mistral['RMSE_Context_Rel'], milvus_mistral['Context_Rel'],
milvus_mistral['RMSE_Context_Util'], milvus_mistral['Util'])
}
for model, (rmse_rel, rel, rmse_util, util) in models.items():
print(f"\n{model}:")
print(f"Context Relevance - Mean: {rel.mean():.3f}, Std: {rel.std():.3f}")
print(f"RMSE Context Rel - Mean: {rmse_rel.mean():.3f}, Std: {rmse_rel.std():.3f}")
print(f"Context Utilization - Mean: {util.mean():.3f}, Std: {util.std():.3f}")
print(f"RMSE Context Util - Mean: {rmse_util.mean():.3f}, Std: {rmse_util.std():.3f}")
def create_violin_plots(milvus_llama, weaviate_mistral, milvus_mistral):
metrics = ['RMSE_Context_Rel', 'RMSE_Context_Util', 'AUCROC']
plt.figure(figsize=(15, 5))
for i, metric in enumerate(metrics, 1):
plt.subplot(1, 3, i)
data = {
'Milvus + LLaMA': milvus_llama[metric].dropna(),
'Weaviate + Mistral': weaviate_mistral[metric].dropna(),
'Milvus + Mistral': milvus_mistral[metric].dropna()
}
sns.violinplot(data=pd.DataFrame(data))
plt.title(f'{metric} Distribution')
plt.xticks(rotation=45)
plt.tight_layout()
plt.savefig('report/visualizations/metric_distributions.png', dpi=300, bbox_inches='tight')
plt.close()
def print_summary_statistics(milvus_llama, weaviate_mistral, milvus_mistral):
print("\nSummary Statistics:")
print("\nMilvus + LLaMA:")
print(milvus_llama.describe().round(4))
print("\nWeaviate + Mistral:")
print(weaviate_mistral.describe().round(4))
print("\nMilvus + Mistral:")
print(milvus_mistral.describe().round(4))
def main():
# Create visualizations directory
import os
os.makedirs("report/visualizations", exist_ok=True)
# Load data
milvus_llama, weaviate_mistral, milvus_mistral = load_and_preprocess_data("report/Scores for RAGBenchCapstone.xlsx")
# Create visualizations
create_performance_comparison(milvus_llama, weaviate_mistral, milvus_mistral)
create_correlation_plots(milvus_llama, weaviate_mistral, milvus_mistral)
create_violin_plots(milvus_llama, weaviate_mistral, milvus_mistral)
# Print statistics
print_summary_statistics(milvus_llama, weaviate_mistral, milvus_mistral)
if __name__ == "__main__":
main() |