基于机器学习推荐预测基于机器学习推荐预测

import random from sklearn.model_selection import train_test_split from sklearn.preprocessing import MinMaxScaler from sklearn import preprocessing from datetime import datetime import time from sklearn.metrics import roc_curve, auc import math from matplotlib import pyplot from sklearn.model_selection import train_test_split from scipy import stats, integrate import seaborn as sns import matplotlib.pyplot as plt from matplotlib.font_manager import FontProperties import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.model_selection import KFold from sklearn.metrics import classification_report from sklearn.model_selection import learning_curve from sklearn.model_selection import validation_curve from sklearn.model_selection import cross_val_score from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from sklearn.metrics import confusion_matrix from sklearn.model_selection import train_test_split from sklearn import metrics from sklearn.svm import SVR, SVC from sklearn.neighbors import KNeighborsClassifier from sklearn.metrics import mean_squared_error, mean_absolute_error # 评价指标 from sklearn.metrics import f1_score, roc_auc_score, accuracy_score from sklearn.linear_model import LogisticRegression plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 data = pd.read_csv("train.csv") # 1 3 7 是 预测列 data.dropna(axis=0, how='any') data = data.fillna(0) print(data.columns) data=data[['用户页面访问持续时间', '跳出率', '网页价值', '浏览器', '信息相关页面访问持续时间', '退出率', '产品相关页面', '产品相关页面访问持续时间', '流量类型', '信息相关页面', '节假日', '区域', '操作系统', '用户相关页面', '是否购买']] print(data.head()) # ['用户页面访问持续时间', '跳出率', '网页价值', '浏览器', '信息相关页面访问持续时间', '退出率', # '产品相关页面', '产品相关页面访问持续时间', '流量类型', '信息相关页面', '节假日', '区域', '操作系统', # '用户相关页面', '是否购买'] data_y = data['是否购买'].values data_x = data[ ['用户页面访问持续时间', '跳出率', '网页价值', '浏览器', '信息相关页面访问持续时间', '退出率', '产品相关页面', '产品相关页面访问持续时间', '流量类型', '信息相关页面', '节假日', '区域', '操作系统', '用户相关页面',]].values x_train, x_test, y_train, y_test = train_test_split(np.array(data_x), np.array(data_y), test_size=0.2) plt.subplots(figsize=(16, 16)) sns.heatmap(data.corr(method='spearman').round(5), annot=True) plt.show() # 设置Axes的标题 data_acc = [] data_f1 = [] # knn算法 knn = KNeighborsClassifier() knn.fit(x_train, y_train) test_pred = knn.predict(x_test) # 进行预测 print("knn算法----------------------------------------- ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) # svm算法 svm = SVC() svm.fit(x_train, y_train) test_pred = svm.predict(x_test) print("svm算法 ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) # RandomForestRClassifier from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import precision_recall_curve, average_precision_score RandomForest= RandomForestClassifier() RandomForest.fit(x_train, y_train) test_pred = RandomForest.predict(x_test) print("RandomForest算法 ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) pred_probas = RandomForest.predict_proba(x_test)[:, 1] fpr, tpr, _ = roc_curve(y_test, pred_probas) roc_auc = auc(fpr, tpr) plt.plot(fpr, tpr, label='area = %.2f' % roc_auc) # 保存到csv文件 df_tmp = pd.DataFrame({'fpr': fpr,'tpr': tpr,}) df_tmp.to_csv('plot.csv', index=False, encoding='utf_8_sig') # 绘制折线图 plt.plot([0, 1], [0, 1], 'k--') plt.xlim([0.0, 1.0]) plt.ylim([0.0, 1.05]) plt.title('ROC曲线') plt.legend(loc='lower right') plt.savefig('ROC曲线.png') plt.show() # pr 曲线 y_score= RandomForest.predict_proba(x_test) y_score=[i[0] for i in y_score] precision, recall, thresholds = precision_recall_curve(y_test, y_score) plt.figure("P-R Curve") plt.title('Precision/Recall Curve') plt.xlabel('Recall') plt.ylabel('Precision') plt.plot(recall, precision) plt.show() # 计算AP AP = average_precision_score(y_test, y_score, average='macro', pos_label=1, sample_weight=None) print('AP:', AP) # AdaBoostClassifier from sklearn.ensemble import AdaBoostClassifier svm = AdaBoostClassifier() svm.fit(x_train, y_train) test_pred = svm.predict(x_test) print("AdaBoost算法 ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) # XGBRClassifier from xgboost import XGBClassifier svm = XGBClassifier() svm.fit(x_train, y_train) test_pred = svm.predict(x_test) print("XGBRegressor算法 ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) # GradientBoosting from sklearn.ensemble import GradientBoostingClassifier svm = GradientBoostingClassifier() svm.fit(x_train, y_train) test_pred = svm.predict(x_test) print("GradientBoosting算法 ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) # LGBMClassifier from lightgbm import LGBMClassifier from lightgbm import LGBMClassifier svm = LGBMClassifier() svm.fit(x_train, y_train) test_pred = svm.predict(x_test) print("LGB算法 ") print(test_pred[:10]) print(y_test[:10]) print("accuracy_score:", accuracy_score(test_pred, y_test)) print("f1_score:", f1_score(test_pred, y_test)) data_acc.append(accuracy_score(test_pred, y_test)) data_f1.append(f1_score(test_pred, y_test)) import matplotlib.pyplot as plt import numpy as np import matplotlib.pyplot as plt import matplotlib as mpl import numpy as np mpl.rcParams["font.sans-serif"] = ["SimHei"] mpl.rcParams["axes.unicode_minus"] = False def zhu_zhuang_tu(label_list, size, title_name, y_name, x_name): """ # 柱状图 label_list = ["第一部分", "第二部分", "第三部分"] size = [55, 35, 10] # 各部分大小 """ fig = plt.figure() plt.bar(label_list, size, 0.5, color="green") plt.xlabel(x_name) plt.ylabel(y_name) plt.title(title_name) plt.show() label_list = ["knn", "svm", "RandomForest", "AdaBoost", "xgboost ", "GradientBoosting", "LGBM"] size = data_acc zhu_zhuang_tu(label_list, size, "算法对比图", "Accuracy", "算法模型") label_list = ["knn", "svm", "RandomForest", "AdaBoost", "xgboost ", "GradientBoosting", "LGBM"] size = data_f1 zhu_zhuang_tu(label_list, size, "算法对比图", "F1_score", "算法模