搭建回归模型

使用房价预测数据搭建回归模型

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__)

2.6.2
sys.version_info(major=3, minor=6, micro=8, releaselevel='final', serial=0)
matplotlib 3.3.4
numpy 1.19.5
pandas 1.1.5
sklearn 0.24.2
tensorflow 2.6.2
keras.api._v2.keras 2.6.0

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

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

# random_state是随机种子，保证代码的可复现性
# train、test的比例默认是3：7
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_valid.shape, y_valid.shape)
print(x_test.shape, y_test.shape)

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

from sklearn.preprocessing import StandardScaler

# 数据归一化
scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

model = keras.models.Sequential([
    keras.layers.Dense(30, activation='relu',
                       input_shape=x_train.shape[1:]),
    keras.layers.Dense(1),
])
model.summary()
model.compile(loss="mean_squared_error", optimizer="sgd")
# EarlyStopping 早停止，patience当连续多少个epochs时验证集精度不再变好终止训练
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-3)]

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_2 (Dense)              (None, 30)                270       
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 31        
=================================================================
Total params: 301
Trainable params: 301
Non-trainable params: 0
_________________________________________________________________

history = model.fit(x_train_scaled, y_train,
                    validation_data = (x_valid_scaled, y_valid),
                    epochs = 100,
                    callbacks = callbacks)

Epoch 1/100
363/363 [==============================] - 1s 1ms/step - loss: 0.8832 - val_loss: 0.6537
Epoch 2/100
363/363 [==============================] - 0s 1ms/step - loss: 0.5799 - val_loss: 0.4851
Epoch 3/100
363/363 [==============================] - 0s 1ms/step - loss: 0.4440 - val_loss: 0.4484
Epoch 4/100
363/363 [==============================] - 0s 1ms/step - loss: 0.4655 - val_loss: 0.4704
Epoch 5/100
363/363 [==============================] - 0s 1ms/step - loss: 0.4152 - val_loss: 0.4224
Epoch 6/100
363/363 [==============================] - 0s 1ms/step - loss: 0.4242 - val_loss: 0.4259
Epoch 7/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3993 - val_loss: 0.4197
Epoch 8/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3942 - val_loss: 0.4121
Epoch 9/100
363/363 [==============================] - 0s 1ms/step - loss: 0.4017 - val_loss: 0.3942
Epoch 10/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3867 - val_loss: 0.3934
Epoch 11/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3774 - val_loss: 0.3887
Epoch 12/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3731 - val_loss: 0.3806
Epoch 13/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3667 - val_loss: 0.3751
Epoch 14/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3886 - val_loss: 0.3786
Epoch 15/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3609 - val_loss: 0.3691
Epoch 16/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3627 - val_loss: 0.3672
Epoch 17/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3686 - val_loss: 0.3693
Epoch 18/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3533 - val_loss: 0.3657
Epoch 19/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3583 - val_loss: 0.4049
Epoch 20/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3488 - val_loss: 0.3684
Epoch 21/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3490 - val_loss: 0.3543
Epoch 22/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3438 - val_loss: 0.3519
Epoch 23/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3427 - val_loss: 0.3505
Epoch 24/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3419 - val_loss: 0.3623
Epoch 25/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3421 - val_loss: 0.3856
Epoch 26/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3403 - val_loss: 0.3461
Epoch 27/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3414 - val_loss: 0.3554
Epoch 28/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3460 - val_loss: 0.3486
Epoch 29/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3369 - val_loss: 0.3491
Epoch 30/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3355 - val_loss: 0.3454
Epoch 31/100
363/363 [==============================] - 0s 1ms/step - loss: 0.3335 - val_loss: 0.3582

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_scaled, y_test, verbose=0)

0.35621199011802673