2-7實戰迴歸模型

#迴歸模型
#regression
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

使用房價資料集

#使用房價資料集
from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()
print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)

.. _california_housing_dataset:

California Housing dataset
--------------------------

**Data Set Characteristics:**

    :Number of Instances: 20640

    :Number of Attributes: 8 numeric, predictive attributes and the target

    :Attribute Information:
        - MedInc        median income in block
        - HouseAge      median house age in block
        - AveRooms      average number of rooms
        - AveBedrms     average number of bedrooms
        - Population    block population
        - AveOccup      average house occupancy
        - Latitude      house block latitude
        - Longitude     house block longitude

    :Missing Attribute Values: None

This dataset was obtained from the StatLib repository.
http://lib.stat.cmu.edu/datasets/

The target variable is the median house value for California districts.

This dataset was derived from the 1990 U.S. census, using one row per census
block group. A block group is the smallest geographical unit for which the U.S.
Census Bureau publishes sample data (a block group typically has a population
of 600 to 3,000 people).

It can be downloaded/loaded using the
:func:`sklearn.datasets.fetch_california_housing` function.

.. topic:: References

    - Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,
      Statistics and Probability Letters, 33 (1997) 291-297

(20640, 8)
(20640,)

import pprint#這個庫會使得列印的好看一點
pprint.pprint(housing.data[0:5])
pprint.pprint(housing.target[0:5])

array([[ 8.32520000e+00,  4.10000000e+01,  6.98412698e+00,
         1.02380952e+00,  3.22000000e+02,  2.55555556e+00,
         3.78800000e+01, -1.22230000e+02],
       [ 8.30140000e+00,  2.10000000e+01,  6.23813708e+00,
         9.71880492e-01,  2.40100000e+03,  2.10984183e+00,
         3.78600000e+01, -1.22220000e+02],
       [ 7.25740000e+00,  5.20000000e+01,  8.28813559e+00,
         1.07344633e+00,  4.96000000e+02,  2.80225989e+00,
         3.78500000e+01, -1.22240000e+02],
       [ 5.64310000e+00,  5.20000000e+01,  5.81735160e+00,
         1.07305936e+00,  5.58000000e+02,  2.54794521e+00,
         3.78500000e+01, -1.22250000e+02],
       [ 3.84620000e+00,  5.20000000e+01,  6.28185328e+00,
         1.08108108e+00,  5.65000000e+02,  2.18146718e+00,
         3.78500000e+01, -1.22250000e+02]])
array([4.526, 3.585, 3.521, 3.413, 3.422])

from sklearn.model_selection import train_test_split
x_train_all,x_test,y_train_all,y_test = train_test_split(
    housing.data,housing.target,random_state=7
)
x_train,x_valid,y_train,y_valid = train_test_split(x_train_all,y_train_all,random_state=11)

print(x_train.shape,y_train.shape)
print(x_test.shape,y_test.shape)
print(x_valid.shape,y_valid.shape)

(11610, 8) (11610,)
(5160, 8) (5160,)
(3870, 8) (3870,)

#資料歸一化
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
x_train_scaler = scaler.fit_transform(x_train)
x_valid_scaler = scaler.transform(x_valid)
x_test_scaler = scaler.transform(x_test)

搭建模型

#搭建模型
model = keras.models.Sequential([
    keras.layers.Dense(30,activation='relu',
                       input_shape=x_train.shape[1:]),#取8
    keras.layers.Dense(1),
])
model.summary()
model.compile(loss="mean_squared_error",optimizer='sgd')
callbacks = [keras.callbacks.EarlyStopping(patience=5,min_delta=1e-3)]

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                (None, 30)                270       
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 31        
=================================================================
Total params: 301
Trainable params: 301
Non-trainable params: 0

history = model.fit(x_train_scaler,y_train,
                    validation_data=(x_valid_scaler,y_valid),
                    epochs=100,
                    callbacks = callbacks)

訓練結果的一部分

Epoch 36/100
363/363 [==============================] - 1s 2ms/step - loss: 0.3469 - val_loss: 0.3647
Epoch 37/100
363/363 [==============================] - 1s 2ms/step - loss: 0.3491 - val_loss: 0.3722
Epoch 38/100
363/363 [==============================] - 1s 2ms/step - loss: 0.3459 - val_loss: 0.3630

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8,5))
    plt.grid(True)
    plt.gca().set_ylim(0,1)
    plt.show()
plot_learning_curves(history)

model.evaluate(x_test_scaler,y_test)

0.3662084639072418