数据来源
澳大利亚降雨预测数据集来自于Kaggle网站：
https://www.kaggle.com/jsphyg/weather-dataset-rattle-package
该数据集该数据集包含来自许多澳大利亚气象站的大约10年的每日天气观测以及天气预报，“RainTomorrow”是要预测的目标变量，这意味着-第二天下雨了，如果当天的降雨量为1mm或更大，则此列为“是”。气象信息包括日期，城市，最低温度，最高温度，降雨量，蒸发量，阳光（一天中阳光明媚的小时数），一天中最强阵风、9am、3pm的风向和风速，一天中9am、3pm的湿度、气压、云层（云层遮盖的天空比例）、温度、当日是否下雨。
该数据集的主要任务目标是根据今日的气象信息训练分类模型，根据该模型预测澳大利亚第二天的降雨。数据总量为145460行，23列。
数据预处理 # -*- coding: utf-8 -*- import pandas as pdfrom sklearn.model_selection import train_test_splitimport numpy as npimport seaborn as snsimport matplotlib.pyplot as pltfrom sklearn.naive_bayes import GaussianNBfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.tree import DecisionTreeClassifierfrom sklearn.tree import export_graphvizfrom sklearn.neighbors import KNeighborsClassifierimport graphvizimport pydotplusimport iopd.set_option(‘display.max_columns’, None)pd.set_option(‘display.max_colwidth’, None)pd.set_option(‘display.max_rows’, 10)pd.set_option(‘display.width’, None)def preprocessing(df, index): labels = set([]) for label in df[index]: labels.add(label) labels = list(labels) # print(labels) print(‘总类别数：’, len(labels)) column = df[index] df.drop(axis=1, columns=index, inplace=True) if ‘RainT’ in index: temp = column.map(lambda x: labels.index(x)) elif index == ‘Date’: temp = column.map(lambda x: x[5] if x[6] == ‘/’ else x[5:7]) else: temp = column.map(lambda x: labels.index(x)+1) df.insert(0, index, temp) return dfdef get_dataset(location): # 获取数据集 df = pd.read_csv(location) # df = df[[‘Location’, ‘MinTemp’, ‘MaxTemp’, ‘Rainfall’, ‘Evaporation’, ‘Sunshine’, ‘WindGustDir’, ‘WindGustSpeed’, # ‘WindSpeed9am’, ‘WindSpeed3pm’, ‘Humidity9am’, ‘Humidity3pm’, ‘Pressure9am’, ‘Pressure3pm’, # ‘Cloud9am’, ‘Cloud3pm’, ‘Temp9am’, ‘Temp3pm’, ‘RainToday’, ‘RainTomorrow’]] print(df) print(df.info()) # 查看缺失值 df = df.dropna() # 去除包含缺失值的行 # 用整数标签代替字符串型数据 for label in [‘Location’, ‘WindGustDir’, ‘WindDir9am’, ‘WindDir3pm’, ‘Date’, ‘RainToday’, ‘RainTomorrow’]: df = preprocessing(df, label) print(df) # Date列格式转换 date = df[‘Date’].astype(float) df.drop(axis=1, columns=’Date’, inplace=True) df.insert(2, ‘Date’, date) print(df.dtypes) print(df.describe()) print(df.corr()[‘RainTomorrow’]) # 打印相关系数矩阵 # 删除相关系数过低的数据 for key in df.corr()[‘RainTomorrow’].keys(): if (df.corr()[‘RainTomorrow’][key] < 0.1) & (df.corr()[‘RainTomorrow’][key] > -0.1): df.drop(axis=1, columns=key, inplace=True) # 画相关性热力图 # sns.heatmap(df.corr()[[‘RainToday’, ‘RainTomorrow’]]) plt.show() return dfdef test(resultset, rightset): # 计算测试集的正确率 print(‘预测结果为’, resultset) print(‘正确结果为’, rightset) if len(resultset) != len(rightset): print(“数据集长度不同, 错误！”) return 0 total = len(resultset) right = 0 for r1, r2 in zip(resultset, rightset): if r1 == r2: right += 1 rightrate = right/total print(rightrate) KNN from tools import *if __name__ == ‘__main__’: df = get_dataset(‘E:\\X\\DATA\\weatherAUS.csv’) df_list = df.values.tolist() feature = df.drop([‘RainTomorrow’], axis=1).values.tolist() label = df[‘RainTomorrow’].values.tolist() feature_train, feature_test, label_train, label_test = train_test_split(feature, label, test_size=0.1) knn = KNeighborsClassifier() knn.fit(feature_test, label_test) result = knn.predict(feature_test) test(result, label_test) 决策树 from tools import *if __name__ == ‘__main__’: df = get_dataset(‘E:\\X\\DATA\\weatherAUS.csv’) print(df) df_list = df.values.tolist() feature = df.drop([‘RainTomorrow’], axis=1).values.tolist() label = df[‘RainTomorrow’].values.tolist() feature_train, feature_test, label_train, label_test = train_test_split(feature, label, test_size=0.1) clf = DecisionTreeClassifier(max_depth=3) clf = clf.fit(feature_train, label_train) test(clf.predict(feature_test), label_test) # 可视化 dot_data = io.StringIO() export_graphviz(clf, out_file=dot_data) graph = pydotplus.graph_from_dot_data(dot_data.getvalue()) graph.write_pdf(“tree.pdf”) 随机森林 from tools import *if __name__ == ‘__main__’: df = get_dataset(‘E:\\X\\DATA\\weatherAUS.csv’) df_list = df.values.tolist() feature = df.drop([‘RainTomorrow’], axis=1).values.tolist() label = df[‘RainTomorrow’].values.tolist() feature_train, feature_test, label_train, label_test = train_test_split(feature, label, test_size=0.1) clf = RandomForestClassifier() clf = clf.fit(feature_train, label_train) print(“随机森林分类”) test(clf.predict(feature_test), label_test) 贝叶斯 from tools import *if __name__ == ‘__main__’: df = get_dataset(‘E:\\X\\DATA\\weatherAUS.csv’) df_list = df.values.tolist() print(df) feature = df.drop([‘RainTomorrow’], axis=1).values.tolist() label = df[‘RainTomorrow’].values.tolist() feature_train, feature_test, label_train, label_test = train_test_split(feature, label, test_size=0.1) clf = GaussianNB() clf.fit(feature_train, label_train) test(clf.predict(feature_test), label_test) 08210063
