ADD file via upload

main.py

@@ -0,0 +1,174 @@
+import argparse
+import json
+import os
+from datetime import timedelta,datetime
+import pandas as pd
+from prophet import Prophet
+from sklearn.linear_model import LogisticRegression
+from sklearn.svm import SVC
+from sklearn.neural_network import MLPClassifier
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+from sklearn.naive_bayes import GaussianNB
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+import joblib
+from src.data_preprocessing import load_data, preprocess_data, split_data
+from src.time_series_prediction import extract_features, label_churners
+ 
+# 数据预处理
+# 从 JSON 文件中加载数据
+with open('commits_data_large.json', 'r') as f:
+    commits = json.load(f)
+             
+# 将数据转换为 DataFrame
+
+df = pd.DataFrame(commits)
+
+# 1.处理缺失值
+df = df.dropna()
+
+# 2. 转换日期时间格式
+df['author_date'] = pd.to_datetime(df['author_date'])
+
+
+#时间序列预测
+def time_series_predict(time_series_data):
+    time_series = Prophet(seasonality_mode='multiplicative').fit(time_series_data)
+    future = time_series.make_future_dataframe()
+    future_time_series_data = time_series.predict(future)
+    return future_time_series_data
+
+def time_series_prediction(time_series_data):
+    return time_series_data
+
+
+# 特征工程
+ 
+
+# 1. 提取时间相关特征
+df['year'] = df['author_date'].dt.year
+df['month'] = df['author_date'].dt.month
+df['day'] = df['author_date'].dt.day
+df['day_of_week'] = df['author_date'].dt.dayofweek
+df['hour'] = df['author_date'].dt.hour
+
+# 2. 计算开发者提交频率
+commit_counts = df.groupby('author_email').size().reset_index(name='commit_count')
+
+# 3. 计算开发者的活跃周期
+df['first_commit_date'] = df.groupby('author_email')['author_date'].transform('min')
+df['last_commit_date'] = df.groupby('author_email')['author_date'].transform('max')
+df['active_days'] = (df['last_commit_date'] - df['first_commit_date']).dt.days
+
+# 4. 合并特征
+df_features = pd.merge(commit_counts, avg_interval, on='author_email')
+df_features = pd.merge(df_features, df[['author_email', 'active_days']].drop_duplicates(), on='author_email')
+
+output_path = 'Dataset.csv'
+df_features.to_csv(output_path, index=False)
+print("数据预处理完成。")
+
+
+# 模型训练
+
+# Load Data
+data = pd.read_csv('dataset.csv', index_col=0)
+# 去掉非数字特征和直接前驱特征
+X = data.loc[:, 'prs': 'sig_cluster'].drop(labels=['last_contribute_to_now', 'user_login_pr'], axis=1)
+print(X)
+
+X = MinMaxScaler().fit_transform(X.values)
+y = data['tag'].values
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=1)
+
+# Results initialize
+results = pd.DataFrame(columns=['Acc', 'Pre', 'Rec', 'F1'],
+                       index=['LR', 'SVM', 'LDA', 'NB', 'KNN', 'NN', 'DT', 'RF', 'GBT'])
+print(results)
+
+# Logistic Regression
+clf = LogisticRegression(random_state=0).fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['LR', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['LR', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['LR', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['LR', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['LR'])
+
+# SVM
+clf = SVC(random_state=0).fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['SVM', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['SVM', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['SVM', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['SVM', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['SVM'])
+
+# NN
+clf = MLPClassifier(random_state=0, max_iter=10000).fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['NN', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['NN', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['NN', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['NN', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['NN'])
+
+# LDA
+clf = LinearDiscriminantAnalysis().fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['LDA', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['LDA', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['LDA', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['LDA', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['LDA'])
+
+# NB
+clf = GaussianNB().fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['NB', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['NB', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['NB', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['NB', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['NB'])
+
+# KNN
+clf = KNeighborsClassifier().fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['KNN', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['KNN', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['KNN', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['KNN', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['KNN'])
+
+# DT
+clf = DecisionTreeClassifier().fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['DT', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['DT', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['DT', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['DT', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['DT'])
+
+# RF
+clf = RandomForestClassifier().fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['RF', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['RF', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['RF', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['RF', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['RF'])
+
+# GBT
+clf = GradientBoostingClassifier().fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+results.loc['GBT', 'Acc'] = accuracy_score(y_test, y_pred)
+results.loc['GBT', 'Pre'] = precision_score(y_test, y_pred)
+results.loc['GBT', 'Rec'] = recall_score(y_test, y_pred)
+results.loc['GBT', 'F1'] = f1_score(y_test, y_pred)
+print(results.loc['GBT'])
+
+print(results)