Keras: utiliser son propre le jeu de données (prix du logement, boston)

On va créer un dossier "data" pour le jeu de données.

Créer un dossier "boston" dedans:

Télécharger le jeu de données (csv) fichier d'ici: https://github.com/shunakanishi/keras_boston_dataset

Déplacer "housing.csv" vers le dossier "boston":

Les données dedans représente ça:

CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD
0.00632	18	2.31	0	0.538	6.575	65.2	4.0900	1
0.02731	0	7.07	0	0.469	6.421	78.9	4.9671	2
0.02729	0	7.07	0	0.469	7.185	61.1	4.9671	2
0.03237	0	2.18	0	0.458	6.998	45.8	6.0622	3
0.06905	0	2.18	0	0.458	7.147	54.2	6.0622	3

TAX	PTRATIO	B	LSTAT	MEDV
296	15.3	396.90	4.98	24.0
242	17.8	396.90	9.14	21.6
242	17.8	392.83	4.03	34.7
222	18.7	394.63	2.94	33.4
222	18.7	396.90	5.33	36.2

Data cited from: http://neupy.com/2015/07/04/boston_house_prices_dataset.html

Maintenant créer "boston.py" dans le dossier partagé et écrire dedans:

import pandas as pd
import numpy as np

# Read dataset into X and Y
df = pd.read_csv('./data/boston/housing.csv', delim_whitespace=True, header=None)
dataset = df.values

X = dataset[:, 0:13]
Y = dataset[:, 13]

# Define the neural network
from keras.models import Sequential
from keras.layers import Dense

def build_nn():
    model = Sequential()
    model.add(Dense(20, input_dim=13, activation='relu', kernel_initializer="normal"))
    # No activation needed in output layer (because regression)
    model.add(Dense(1, kernel_initializer="normal"))

    # Compile Model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model

# Evaluate model (kFold cross validation)
from keras.wrappers.scikit_learn import KerasRegressor

# sklearn imports:
from sklearn.cross_validation import cross_val_score, KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

# Before feeding the i/p into neural-network, standardise the dataset because all input variables vary in their scales
estimators = []
estimators.append(('standardise', StandardScaler()))
estimators.append(('multiLayerPerceptron', KerasRegressor(build_fn=build_nn, nb_epoch=100, batch_size=32, verbose=1)))

pipeline = Pipeline(estimators)

kfold = KFold(n=len(X), n_folds=10)
results = cross_val_score(pipeline, X, Y, cv=kfold)

print ("");
print ("Mean: ", results.mean())
print ("StdDev: ", results.std())

Faire ce commande:

$ sudo python3.5 boston.py

L'apprentissage profond va démarrer avec les données de housing.csv:

Moyenne: 478.48

Écart-type: 258.5499