Keras的泰坦尼克号的生存率的数据分析

 

 # coding: utf-8

 # In[1]:

 import urllib.request
 import os

 # In[2]:

 url="http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic3.xls"
 filepath="titanic3.xls"
 if not os.path.isfile(filepath):
     result=urllib.request.urlretrieve(url,filepath)
     print('downloaded:',result)

 # In[3]:

 import numpy
 import pandas as pd

 # In[4]:

 all_df = pd.read_excel(filepath)

 # In[5]:

 all_df[:5]

 # In[6]:

 cols=['survived','name','pclass' ,'sex', 'age', 'sibsp',
       'parch', 'fare', 'embarked']
 all_df=all_df[cols]
 all_df[:5]

 # In[7]:

 all_df.isnull().sum()

 # In[8]:

 df=all_df.drop(['name'], axis=1)
 df[:20]

 # In[9]:

 age_mean = df['age'].mean()
 df['age'] = df['age'].fillna(age_mean)
 df[:20]

 # In[10]:

 fare_mean = df['fare'].mean()
 df['fare'] = df['fare'].fillna(fare_mean)

 # In[11]:

 df['sex']= df['sex'].map({'female':0, 'male': 1}).astype(int)

 # In[12]:

 df[:2]

 # In[13]:

 x_OneHot_df = pd.get_dummies(data=df,columns=["embarked" ])

 # In[14]:

 x_OneHot_df[:2]

 # In[15]:

 ndarray = x_OneHot_df.values
 ndarray.shape

 # In[16]:

 ndarray[:2]

 # In[17]:

 Label = ndarray[:,0]
 Features = ndarray[:,1:]

 # In[18]:

 Features[:2]

 # In[19]:

 from sklearn import preprocessing
 minmax_scale = preprocessing.MinMaxScaler(feature_range=(0, 1))
 scaledFeatures=minmax_scale.fit_transform(Features)
 scaledFeatures[:2]

 # In[20]:

 msk = numpy.random.rand(len(all_df)) < 0.8
 train_df = all_df[msk]
 test_df = all_df[~msk]

 # In[21]:

 msk

 # In[22]:

 print('total:',len(all_df),
       'train:',len(train_df),
       'test:',len(test_df))

 # In[23]:

 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

 # In[24]:

 train_Features,train_Label=PreprocessData(train_df)
 test_Features,test_Label=PreprocessData(test_df)

 # In[25]:

 train_Features[:2]

 # In[26]:

 train_Label[:2]

 # In[27]:

 from keras.models import Sequential
 from keras.layers import Dense,Dropout

 # In[28]:

 model = Sequential()
 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'))
 model.summary()

 # In[29]:

 model.compile(loss='binary_crossentropy',
               optimizer='adam', metrics=['accuracy'])
 train_history =model.fit(x=train_Features,
                          y=train_Label,
                          validation_split=0.1,
                          epochs=30,
                          batch_size=30,verbose=2)

 # In[30]:

 import matplotlib.pyplot as plt
 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')

 # In[31]:

 scores = model.evaluate(x=test_Features,
                         y=test_Label)
 scores

 # In[32]:

 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])
 all_df[-2:]

 # In[33]:

 all_Features,Label=PreprocessData(all_df)
 all_probability=model.predict(all_Features)
 all_probability[:10]

 # In[34]:

 pd=all_df
 pd.insert(len(all_df.columns),
           'probability',all_probability)
 pd[-2:]

 # In[35]:

 pd[(pd['survived']==0) &  (pd['probability']>0.9) ]

 # In[36]:

 pd[:5]

 # In[ ]:

 # In[ ]:

excel资源如下：

链接：https://pan.baidu.com/s/1PvonynplLKC6ZepSlL9DqQ
提取码：w7z3

采用多层感知器的方案的，主要是特点是针对数据的预处理过程。对excel表格的处理。

读取文件显示前五行：

筛选出表内的指定列：

去掉名字列生成新数据：

查找未知信息null，然后补充为平均值

修改性别样式从male和female到0和1：

将DF中的数据某列拆分：

提取目标输出数据和输入数据：

将输入数据转化为0-1之间的数据方式：

随机分割数据2:8作为测试数据和训练数据的方案！：

之后建立模型，两个隐层，计算方式为上一层神经元乘下一层神经元，加偏差下一层神经元。

之后计算，绘图，预测。

插入两行数据到总数据：

之后计算预测，找到生存概率。

筛选出实际数据为0而预测数据为存活的数据：

可以找到他们之所以没有存活的背后感人故事。。。。。。