机器学习代码学习(四)->>泰坦尼克号

傷城~ 2022-05-06 10:42 362阅读 0赞

下面代码为: .ipynb文件, 可以在Jupyter上运行  
题目为:  
给了3个.csv文件(一个训练, 一个测试,一个预测)  
求: 预测乘客生还是死

import numpy as np#处理矩阵
    import pandas as pd#资料处理(读csv文件)
    import matplotlib.pyplot as plt#画图
    import seaborn as sns
    
    import warnings
    warnings.filterwarnings('ignore')
    
    #读入文件
    %matplotlib inline
    train= pd.read_csv('/Users/liyixin/Desktop/AI/third-titanic/train.csv')#训练
    test2= pd.read_csv('/Users/liyixin/Desktop/AI/third-titanic/test_ti.csv')#测试
    test= pd.read_csv('/Users/liyixin/Desktop/AI/third-titanic/test.csv')#预测
    
    #数据处理(训练,测试,预测)
    #drop:将无关的属性拿掉(职全为1)-Name,Ticket,Cabin;拿掉后,其他的位置不变
    train = train.drop(["Name", "Ticket"], axis=1)
    test = test.drop(["Name", "Ticket"], axis=1)
    test2 = test2.drop(["Name", "Ticket"], axis=1)
    
    train = train.drop(["Cabin"], axis=1)
    test = test.drop(["Cabin"], axis=1)
    test2 = test2.drop(["Cabin"], axis=1)
    
    #loc:将male和female转化成0,1
    train.loc[train["Sex"]=="male", "Sex"] = 1
    train.loc[train["Sex"]=="female", "Sex"] = 0
    test.loc[test["Sex"]=="male", "Sex"] = 1
    test.loc[test["Sex"]=="female", "Sex"] = 0
    test2.loc[test2["Sex"]=="male", "Sex"] = 1
    test2.loc[test2["Sex"]=="female", "Sex"] = 0
    
    #fillna:补S,众数
    train["Embarked"] = train["Embarked"].fillna("S")
    test2["Embarked"] = test2["Embarked"].fillna("S")
    
    train.loc[train["Embarked"]=="S", "Embarked"] = 0
    train.loc[train["Embarked"]=="C", "Embarked"] = 1
    train.loc[train["Embarked"]=="Q", "Embarked"] = 2
    test.loc[test["Embarked"]=="S", "Embarked"] = 0
    test.loc[test["Embarked"]=="C", "Embarked"] = 1
    test.loc[test["Embarked"]=="Q", "Embarked"] = 2
    test2.loc[test2["Embarked"]=="S", "Embarked"] = 0
    test2.loc[test2["Embarked"]=="C", "Embarked"] = 1
    test2.loc[test2["Embarked"]=="Q", "Embarked"] = 2
    #票价为空,补中位数的值median
    test["Fare"]=test['Fare'].fillna(test['Fare'].median(),inplace=True)
    
    
    average_age_train   = train["Age"].mean()#平均数
    std_age_train       = train["Age"].std()#中位数
    count_nan_age_train = train["Age"].isnull().sum()
    
    
    average_age_test   = test["Age"].mean()
    std_age_test       = test["Age"].std()
    count_nan_age_test = test["Age"].isnull().sum()
    
    average_age_test2  = test2["Age"].mean()
    std_age_test2      = test2["Age"].std()
    count_nan_age_test2 = test2["Age"].isnull().sum()
    
    #random用公式: (平均-中位,平均+中位,~)来补空位
    rand_1 = np.random.randint(average_age_train - std_age_train, average_age_train + std_age_train, size = count_nan_age_train)
    rand_2 = np.random.randint(average_age_test - std_age_test, average_age_test + std_age_test, size = count_nan_age_test)
    rand_3 = np.random.randint(average_age_test2 - std_age_test2, average_age_test2 + std_age_test2, size = count_nan_age_test2)
    
    #loc: 补在哪一行
    train.loc[np.isnan(train["Age"]), "Age"] = rand_1
    test.loc[np.isnan(test["Age"]), "Age"] = rand_2
    test2.loc[np.isnan(test2["Age"]), "Age"] = rand_3
        
    #astype: 年龄String->int
    train['Age'] = train['Age'].astype(int)
    test['Age']    = test['Age'].astype(int)
    test2['Age']    = test2['Age'].astype(int)

from sklearn import preprocessing#数据标准化(max-min)->减少range
    from keras import utils as np_utils
    #drop: id和survived(输入和答案单独拿出来)->转Array
    X_train = train.drop(["PassengerId", "Survived"], axis=1)
    y_train = train["Survived"]
    
    X_test2 = test2.drop(["PassengerId", "Survived"], axis=1)
    y_test2 = test2["Survived"]
    
    X_test  = test.drop(["PassengerId"],axis=1)
    #->转Array
    X_train = np.array(X_train).astype('float32')
    y_train = np.array(y_train).astype('int32')
    
    X_test2 = np.array(X_test2).astype('float32')
    y_test2 = np.array(y_test2).astype('int32')
    #minmax——scale标准化方法 range在(0,1)之间
    minmax_scale = preprocessing.MinMaxScaler(feature_range=(0,1))
    X_train_norm=minmax_scale.fit_transform(X_train)
    #onehot编码 要的1,其他为0 [0,1]与[1,0]
    #np_utils与to_categorical是pandas的function
    y_train_onehot = np_utils.to_categorical(y_train, 2)
    
    X_test2_norm=minmax_scale.fit_transform(X_test2)
    #np_utils与to_categorical是pandas的function
    y_test2_onehot = np_utils.to_categorical(y_test2, 2)
    X_test = np.array(X_test).astype('float32')

from keras.layers.normalization import BatchNormalization#训练模型
    from keras.models import Sequential#Sequential是线性model
    from keras.utils import np_utils# np_utils正规化
    from keras.layers import Dense,Dropout#Dense是层 ,Dropout过度学习
    model = Sequential()#线性model->NET架构
    #input(7个特征)
    #参数: units=256 input_dim=7(7个特征) kernel_initializer选择数学方法
    # activation选择记忆力函数(sigmoid /...)
    model.add(Dense(units=512,input_dim=7,kernel_initializer='random_uniform',activation='sigmoid'))
    model.add(Dropout(0.25))#过度学习
    model.add(Dense(units=128,kernel_initializer='random_uniform',activation='sigmoid'))
    model.add(Dropout(0.25))
    model.add(Dense(units=32,kernel_initializer='random_uniform',activation='sigmoid'))
    model.add(Dropout(0.25))
    #output(2个特征)
    model.add(Dense(units=2,kernel_initializer='random_uniform',activation='softmax'))
    model.summary()#摘要

from keras import optimizers#优化器
    #binary_crossentropy二分法 ( sgd:60% ->rmsprop:80% ) 
    model.compile(loss='binary_crossentropy',optimizer='rmsprop',metrics=['accuracy'])

import keras
    from keras.callbacks import ModelCheckpoint
    from keras.callbacks import EarlyStopping
    checkpointer = ModelCheckpoint(filepath='C:\\input\\NNModel.h5', verbose=1, save_best_only=True)
    early=EarlyStopping(monitor='val_loss', min_delta=0, patience=0, verbose=0, mode='auto', baseline=None)
    call_list=[checkpointer,early]
    #model.fit训练的方式 
    train_history = model.fit(x=X_train_norm,
                             y=y_train_onehot,
                             validation_split=0.1,
                             epochs=100,#训练的多少,找最低点
                             batch_size=128,verbose=1)
    #结果中: loss与val_loss

import matplotlib.pyplot as plt  #画图,画出loss与val_loss
    def show_train_history(train_history, train, validation):  
        plt.plot(train_history.history[train])  
        plt.plot(train_history.history[validation])  
        plt.title('Train History')  
        plt.ylabel(train)  
        plt.xlabel('Epoch')  
        plt.legend(['train', 'validation'], loc='upper left')  
        plt.show()

show_train_history(train_history,'acc','val_acc')

show_train_history(train_history,'loss','val_loss')

scores = model.evaluate(x=X_test2_norm,#model.evaluate检测(100笔数据)->用于测试准确度(0.81)
                            y=y_test2_onehot)
    scores[1]

prediction = model.predict_classes(X_test2_norm)  # Making prediction and save result to prediction

import pandas as pd  
    print("\t[Info] Display Confusion Matrix:")  
    print("%s\n" % pd.crosstab(y_test2, prediction, rownames=['label'], colnames=['predict'])) 
    #结果中: 0表示死,1表示活

Y_pred=model.predict_classes(X_test)

s=({"PassengerId":test["PassengerId"],"Survived":Y_pred})
    submit=pd.DataFrame(data=s)
    submit.to_csv('/Users/liyixin/Desktop/AI/third-titanic/titanic.csv',index=False)