Update app.py

app.py

@@ -1323,50 +1323,6 @@ df = pd.DataFrame(results)
 summary = df.groupby("k")[["precision", "recall", "f1"]].mean().round(3)
 print(summary)
 
-import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
-
-# Load the dataset
-df = pd.read_csv("/Users/husseinelsaadi/kaggle-local-project/data/retrieval_metrics_table.csv")
-
-# Set plot style
-sns.set(style="whitegrid")
-
-# Plot 1: Precision per Job Role
-plt.figure(figsize=(12, 6))
-sns.barplot(data=df, x="job_role", y="precision")
-plt.title("Precision@K per Job Role")
-plt.xticks(rotation=45, ha="right")
-plt.tight_layout()
-plt.show()
-
-# Plot 2: Recall per Job Role
-plt.figure(figsize=(12, 6))
-sns.barplot(data=df, x="job_role", y="recall")
-plt.title("Recall@K per Job Role")
-plt.xticks(rotation=45, ha="right")
-plt.tight_layout()
-plt.show()
-
-# Plot 3: F1 Score per Job Role
-plt.figure(figsize=(12, 6))
-sns.barplot(data=df, x="job_role", y="f1")
-plt.title("F1@K per Job Role")
-plt.xticks(rotation=45, ha="right")
-plt.tight_layout()
-plt.show()
-
-# Plot 4: Grouped Bar Chart for Precision, Recall, F1
-df_melted = df.melt(id_vars="job_role", value_vars=["precision", "recall", "f1"], 
-                    var_name="Metric", value_name="Score")
-plt.figure(figsize=(14, 6))
-sns.barplot(data=df_melted, x="job_role", y="Score", hue="Metric")
-plt.title("Retrieval Evaluation Metrics per Job Role")
-plt.xticks(rotation=45, ha="right")
-plt.legend(title="Metric")
-plt.tight_layout()
-plt.show()
 
 def extract_job_details(job_description):
     """Extract job details such as title, skills, experience level, and years of experience from the job description."""