本文共 5633 字，大约阅读时间需要 18 分钟。

本文将介绍：

• 加载Titanic数据集
• 使用feature_column做数据处理,并转化为tf.data.dataset类型数据
• keras_to_estimator

一，加载Titanic数据集

1，下载Titanic数据集,使用pandas读取并解析数据集

# 在如下的两个网址下载数据# https://storage.googleapis.com/tf-datasets/titanic/train.csv# https://storage.googleapis.com/tf-datasets/titanic/eval.csvimport matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport timeimport tensorflow as tffrom tensorflow import keras# 打印使用的python库的版本信息print(tf.__version__)print(sys.version_info)for module in mpl, np, pd, sklearn, tf, keras:    print(module.__name__, module.__version__)train_file = "./data/titanic/train.csv"eval_file = "./data/titanic/eval.csv"train_df = pd.read_csv(train_file)eval_df = pd.read_csv(eval_file)print(train_df.head()) # 默认取出前5条数据print(eval_df.head())

2，分离出特征值和目标值

y_train = train_df.pop('survived')y_eval = eval_df.pop('survived')print(train_df.head())print(eval_df.head())print(y_train.head())print(y_eval.head())

3，使用panda对数值型数据的字段进行统计

print(train_df.describe())# ---output------              age  n_siblings_spouses       parch        farecount  627.000000          627.000000  627.000000  627.000000mean    29.631308            0.545455    0.379585   34.385399std     12.511818            1.151090    0.792999   54.597730min      0.750000            0.000000    0.000000    0.00000025%     23.000000            0.000000    0.000000    7.89580050%     28.000000            0.000000    0.000000   15.04580075%     35.000000            1.000000    0.000000   31.387500max     80.000000            8.000000    5.000000  512.329200

4,查看数据集中的测试集,验证集的数据维度

print(train_df.shape, eval_df.shape)# ---output------(627, 9) (264, 9)

5,使用pands中的matplotlib绘制图表,更直观的了解数据

1）统计-年龄直观图

train_df.age.hist(bins = 50)# bins是将所有数据分为多少份

2）统计-性别直观图

# value_counts() --> 将value归类并按类计数train_df.sex.value_counts().plot(kind = 'barh') # 横向的柱状图是"barh";纵向的柱状图"bar"

3）统计-不同仓位的乘客各有多少

train_df['class'].value_counts().plot(kind = 'barh')

4）统计-在Titanic中,男性有多少人获救了,女性有多少人获救了

pd.concat([train_df, y_train], axis = 1).groupby('sex').survived.mean()pd.concat([train_df, y_train], axis = 1).groupby('sex').survived.mean().plot(kind='barh')

二，使用feature_column做数据处理,并转化为tf.data.dataset类型数据

1，将"离散特征"和"连续特征"整合为one-hot编码

1）将特征分为"离散特征"和"连续特征"两个列表

categorical_columns = ['sex', 'n_siblings_spouses', 'parch', 'class','deck', 'embark_town', 'alone']numeric_columns = ['age', 'fare']feature_columns = []

2）使用tf.feature_column对"离散特征"做处理

for categorical_column in categorical_columns:    vocab = train_df[categorical_column].unique()    print(categorical_column, vocab)    feature_columns.append(        tf.feature_column.indicator_column(            tf.feature_column.categorical_column_with_vocabulary_list(                categorical_column, vocab)))                # ---output------sex ['male' 'female']n_siblings_spouses [1 0 3 4 2 5 8]parch [0 1 2 5 3 4]class ['Third' 'First' 'Second']deck ['unknown' 'C' 'G' 'A' 'B' 'D' 'F' 'E']embark_town ['Southampton' 'Cherbourg' 'Queenstown' 'unknown']alone ['n' 'y']

3）使用tf.feature_column对"连续特征"做处理

for categorical_column in numeric_columns:    feature_columns.append(        tf.feature_column.numeric_column(            categorical_column, dtype=tf.float32))

2，将ndarray数据转化为tf.data.dataset中的BatchDataset类型数据

def make_dataset(data_df, label_df, epochs = 10, shuffle = True,batch_size = 32):    dataset = tf.data.Dataset.from_tensor_slices((dict(data_df), label_df))    if shuffle:        dataset = dataset.shuffle(10000)    dataset = dataset.repeat(epochs).batch(batch_size)    return datasettrain_dataset = make_dataset(train_df, y_train, batch_size = 5)# 查看转化后的tf.data.dataset中的一条数据的信息for x, y in train_dataset.take(1):    print(x, y)# ---output---------{
   'sex': 
   
    , 'age': 
    
     , 'n_siblings_spouses': 
     
      , 'parch': 
      
       , 'fare': 
       
        , 'class': 
        
         , 'deck': 
         
          , 'embark_town': 
          
           , 'alone': 
           
            } tf.Tensor([0 1 0 0 0], shape=(5,), dtype=int32)
           
          
         
        
       
      
     
    
   

3，使用keras.layers.DenseFeature将一条数据其中两个字段转化为one-hot处理后的数据

# keras.layers.DenseFeaturefor x, y in train_dataset.take(1):    age_column = feature_columns[7]    gender_column = feature_columns[0]    print(keras.layers.DenseFeatures(age_column)(x).numpy())    print(keras.layers.DenseFeatures(gender_column)(x).numpy())# ---output----------[[28.] [50.] [27.] [28.] [32.]][[1. 0.] [0. 1.] [0. 1.] [0. 1.] [1. 0.]]

4，使用keras.layers.DenseFeature将一条数据中所有字段转化为one-hot处理后的数据

# keras.layers.DenseFeaturefor x, y in train_dataset.take(1):    print(keras.layers.DenseFeatures(feature_columns)(x).numpy())

三，keras_to_estimator

1，定义keras模型,输入层输入为转化为one-hot处理后的数据

model = keras.models.Sequential([    keras.layers.DenseFeatures(feature_columns),    keras.layers.Dense(100, activation='relu'),    keras.layers.Dense(100, activation='relu'),    keras.layers.Dense(2, activation='softmax'),])model.compile(loss='sparse_categorical_crossentropy',              optimizer = keras.optimizers.SGD(lr=0.01),              metrics = ['accuracy'])

2，训练模型

训练模型可以使用如下两种方法：

1）使用普通的model模型训练

train_dataset = make_dataset(train_df, y_train, epochs = 100)eval_dataset = make_dataset(eval_df, y_eval, epochs = 1, shuffle = False)history = model.fit(train_dataset,                    validation_data = eval_dataset,                    steps_per_epoch = 19,                    validation_steps = 8,                    epochs = 100)

2）使用转化为estimator后的model模型训练

注：在tensorflow2中该方法还存在bug，待解决。

estimator = keras.estimator.model_to_estimator(model)# 1. function# 2. return a. (features, labels) b. dataset -> (feature, label)estimator.train(input_fn = lambda : make_dataset(    train_df, y_train, epochs=100))

转载地址：http://svili.baihongyu.com/