Removed the temp. visualization script

t4.py

-import pandas as pd
-import matplotlib.pyplot as plt
-import json
-
-input_file = 'C:/Users/91991/Desktop/detailed_commits_info.json'
-
-# Initialize an empty list to store JSON objects
-data_list = []
-
-# Read JSON data line by line and load each line as JSON
-# with open(input_file, 'r') as f:
-#     for line in f:
-#         data = json.loads(line)
-#         data_list.append(data)
-
-# df = pd.DataFrame(data_list)
-
-df = pd.read_json(input_file)
-print(df)
-# Check for missing data
-print("Missing Data Summary:")
-print(df.isnull().sum())
-
-# Perform analysis and visualization
-# For example, let's assume the JSON structure contains 'Key', 'addedFiles', 'deletedFiles', 'modifiedFiles' fields.
-
-# Top 10 decision keys with most number of added, deleted, or modified files
-#grp = df.groupby('Key')[['Number_of_added_files', 'Number_of_deleted_files', 'Number_of_modified_files']].sum()
-#grp['Total'] = grp.sum(axis=1)
-#top_10 = grp.nlargest(10, 'Total')
-# top_10[['Number_of_added_files', 'Number_of_deleted_files', 'Number_of_modified_files']].plot(kind='bar', stacked=True)
-# plt.xlabel('K')
-# plt.ylabel('Total added, deleted, and modified files')
-# plt.title('Stacked Bar Chart for Top 10 decision keys')
-# plt.show()
-
-# Decision keys with averages of extremely high risk and low risk unit size
-# Assuming JSON structure contains 'Key' and 'DMM_UNIT_SIZE' fields
-grp_data = df.groupby('Key')['DMM_unit_size'].mean()
-filtered_k_high = grp_data[grp_data >= 0.8]
-filtered_k_low = grp_data[grp_data <= 0.2]
-plt.figure(figsize=(10, 6))
-plt.bar(filtered_k_high.index, filtered_k_high.values, color='blue', label='Mean X >= 0.8')
-plt.bar(filtered_k_low.index, filtered_k_low.values, color='red', label='Mean X < 0.2')
-plt.xlabel('Decision Keys', fontsize=8)
-plt.ylabel('Mean Unit Size')
-plt.title('Decision Keys with High risk and Low Risk Unit Size')
-plt.legend()
-plt.grid(True)
-plt.tight_layout()
-plt.show()
-
-for Key, grp_data in df.groupby("Key"):
-    grp_data.boxplot(column=["DMM_unit_size", "DMM_unit_complexity", "DMM_unit_interfacing"])
-    plt.title(f"Boxplots for Key '{Key}'")
-    plt.ylabel("Values")
-    plt.xlabel("Variables")
-    plt.show()
-
-grp_complexity = df.groupby('Key')['complexity'].mean().reset_index()
-filtered_grouped = grp_complexity[grp_complexity['complexity'] >= 200]
-plt.figure(figsize=(10, 6))
-plt.bar(filtered_grouped['Key'], filtered_grouped['complexity'])
-plt.xlabel('Decision Key')
-plt.ylabel('Average Complexity')
-plt.title('Decision Keys with Average Complexity greater than 200')
-plt.xticks(rotation=45, ha='right')
-plt.tight_layout()
-plt.show()