從零基礎入門Tensorflow2.0 ----五、20. 預定義estimator使用

every blog every motto:

0. 前言

預定義estimator的使用

1. 代碼部分

1. 導入模塊

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl,np,pd,sklearn,tf,keras:
    print(module.__name__,module.__version__)

2. 讀取數據

# 讀取數據
train_file = './data/train.csv'
eval_file = './data/eval.csv'

train_df = pd.read_csv(train_file)
eval_df = pd.read_csv(eval_file)

print(train_df.head())
print(eval_df.head())

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. feature_columns

# 離散特徵
categorical_colums = ['sex','n_siblings_spouses','parch','class','deck','embark_town','alone']
numerical_columns = ['age','fare']

feature_columns = []
# 離散
for categorical_column in categorical_colums:
    vocab = train_df[categorical_column].unique() # 獲取所有可能的值
    print(categorical_column,vocab)
    # one-hot 編碼，
    feature_columns.append(
        tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list(categorical_column,vocab)))

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

4. 構建dataset

# 構建dataset
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 dataset

5. 保存輸出模型

5.1.1 baseline_estimator

# 保存輸出模型
output_dir = 'baseline_model'
if not os.path.exists(output_dir):
    os.mkdir(output_dir)

baseline_estimator = tf.estimator.BaselineClassifier(model_dir = output_dir,n_classes=2)
baseline_estimator.train(input_fn = lambda:make_dataset(train_df,y_train,epochs=100))

5.2 evaluate

baseline_estimator.evaluate(input_fn = lambda : make_dataset(eval_df,y_eval,epochs=1,shuffle=False,batch_size=20))

5.2.1 linear

linear_ouput_dir = 'linear_model'
if not os.path.exists(linear_ouput_dir):
    os.mkdir(linear_ouput_dir)
linear_estimator = tf.estimator.LinearClassifier(model_dir=linear_ouput_dir,n_classes=2,feature_columns=feature_columns)
linear_estimator.train(input_fn=lambda :make_dataset(train_df,y_train,epochs=100))

5.2.5 evaluate

linear_estimator.evaluate(input_fn=lambda :make_dataset(eval_df,y_eval,epochs=1,shuffle=False))

5.3.1 dnn_estimator

dnn_output_dir = './dnn_model'
if not os.path.exists(dnn_output_dir):
    os.mkdir(dnn_output_dir)
dnn_estimator = tf.estimator.DNNClassifier(model_dir=dnn_output_dir,n_classes=2,feature_columns=feature_columns,
                                          hidden_units=[128,128],activation_fn=tf.nn.relu,optimizer='Adam')
dnn_estimator.train(input_fn=lambda : make_dataset(train_df,y_train,epochs=100))

5.3.2 evaluate

dnn_estimator.evaluate(input_fn=lambda : make_dataset(eval_df,y_eval,epochs=1,shuffle=False))