1.导入运行库
import numpy
import pandas as pd
from sklearn import preprocessing
numpy.random.seed(10)
2.数据准备
all_df = pd.read_excel("data/titanic3.xls")
#去除无用数据
cols=['survived','name','pclass' ,'sex', 'age', 'sibsp',
'parch', 'fare', 'embarked']
all_df=all_df[cols]
#划分训练和测试集
msk = numpy.random.rand(len(all_df)) < 0.8
train_df = all_df[msk]
test_df = all_df[~msk]
#定义数据预处理函数
def PreprocessData(raw_df):
df=raw_df.drop(['name'], axis=1)
age_mean = df['age'].mean()
df['age'] = df['age'].fillna(age_mean)
fare_mean = df['fare'].mean()
df['fare'] = df['fare'].fillna(fare_mean)
df['sex']= df['sex'].map({'female':0, 'male': 1}).astype(int)
x_OneHot_df = pd.get_dummies(data=df,columns=["embarked" ])
ndarray = x_OneHot_df.values
Features = ndarray[:,1:]
Label = ndarray[:,0]
minmax_scale = preprocessing.MinMaxScaler(feature_range=(0, 1))
scaledFeatures=minmax_scale.fit_transform(Features)
return scaledFeatures,Label
#对已经划分好的数据集进行预处理
train_Features,train_Label=PreprocessData(train_df)
test_Features,test_Label=PreprocessData(test_df)
3.建立模型(全连接)
from keras.models import Sequential
from keras.layers import Dense,Dropout
#建立堆叠基础模型
model = Sequential()
#建立两层全连接,和输出两种情况的输出层
model.add(Dense(units=40, input_dim=9,
kernel_initializer='uniform',
activation='relu'))
model.add(Dense(units=30,
kernel_initializer='uniform',
activation='relu'))
model.add(Dense(units=1,
kernel_initializer='uniform',
activation='sigmoid'))
4.训练模型
#定义模型格式
model.compile(loss='binary_crossentropy',
optimizer='adam', metrics=['accuracy'])
#导入训练数据
train_history =model.fit(x=train_Features,
y=train_Label,
validation_split=0.1,
epochs=30,
batch_size=30,verbose=1)
5.打印过程中的准确度和损失值
import matplotlib.pyplot as plt
#建立打印准确度和损失值的函数
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')
6.模型准确率计算
scores = model.evaluate(x=test_Features,
y=test_Label)
print(scores[1])
7.加入主人公jack和rose的数据
Jack = pd.Series([0 ,'Jack',3, 'male' , 23, 1, 0, 5.0000,'S'])
Rose = pd.Series([1 ,'Rose',1, 'female', 20, 1, 0, 100.0000,'S'])
JR_df = pd.DataFrame([list(Jack),list(Rose)],
columns=['survived', 'name','pclass', 'sex',
'age', 'sibsp','parch', 'fare','embarked'])
all_df=pd.concat([all_df,JR_df])
8.对所有数据进行预测
#对所有数据进行数据预处理
all_Features,Label=PreprocessData(all_df)
#进行预测
all_probability=model.predict(all_Features)
#在原有数据中添加生还几率的列
pd=all_df
pd.insert(len(all_df.columns),
'probability',all_probability)
- 查看生还几率高缺没有生还的人
pd[(pd['survived']==0) & (pd['probability']>0.9) ]