tf.keras.utils.get_file

/Users/csian/.keras/datasets/auto-mpg.data

import pandas as pd

dataset_path=tf.keras.utils.get_file("auto-mpg.data", ("http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data"))

column_names=['MPG', 'Cylinders', 'Displacement', 'Horsepower', 'Weight', 'Acceleration', 'ModelYear', 'Origin']

df=pd.read_csv(dataset_path, names=column_names, na_values='?', comment='\t', sep=' ', skipinitialspace=True)

df=df.dropna()

df=df.reset_index(drop=True)

import sklearn

import sklearn.model_selection

df_train, df_test=sklearn.model_selection.train_test_split(df, train_size=0.8)

train_stats=df_train.describe().transpose()

numeric_column_names=[

'Cylinders', 'Displacement', 'Horsepower', 'Weight', 'Acceleration']

df_train_norm, df_test_norm=df_train.copy(), df_test.copy()

for col_name in numeric_column_names:

mean=train_stats.loc[col_name, 'mean']

std=train_stats.loc[col_name, 'std']

df_train_norm.loc[:, col_name]=(df_train_norm.loc[: ,col_name]-mean)/std

df_test_norm.loc[:, col_name]=(df_train_norm.loc[: ,col_name]-mean)/std

feature_column(for keras.estimator)

#연속 수치열 데이터

numeric_features=[]

for col_name in numeric_column_names:

numeric_features.append(tf.feature_column.numeric_column(key=col_name))

#순서 있는 범주

feature_year=tf.feature_column.numeric_column(key='ModelYear')

bucketized_features=[]

bucketized_features.append(tf.feature_column.bucketized_column(source_column=feature_year, boundaries=[73, 76, 79]))

#순서 없는 범주 & 밀집 열 변형

feature_origin=tf.feature_column.categorical_column_with_vocabulary_list(

key='Origin', vocabulary_list=[1, 2, 3])

categorical_indicator_features=[]

categorical_indicator_features.append(tf.feature_column.indicator_column(feature_origin))

Auto MPG