PS: 个人笔记，建议不看
原书资料：https://github.com/ageron/handson-ml2
2.1数据获取
import pandas as pd
data = pd.read_csv(r"C:\Users\cyan\Desktop\AI\ML\handson-ml2\datasets\housing\housing.csv")
data.head()
data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20640 entries, 0 to 20639
Data columns (total 10 columns):# Column Non-Null Count Dtype
--- ------ -------------- ----- 0 longitude 20640 non-null float641 latitude 20640 non-null float642 housing_median_age 20640 non-null float643 total_rooms 20640 non-null float644 total_bedrooms 20433 non-null float645 population 20640 non-null float646 households 20640 non-null float647 median_income 20640 non-null float648 median_house_value 20640 non-null float649 ocean_proximity 20640 non-null object
dtypes: float64(9), object(1)
memory usage: 1.6+ MB
data.columns
Index(['longitude', 'latitude', 'housing_median_age', 'total_rooms','total_bedrooms', 'population', 'households', 'median_income','median_house_value', 'ocean_proximity'],dtype='object')
data['ocean_proximity'].value_counts().plot()
data.describe()
| longitude | latitude | housing_median_age | total_rooms | total_bedrooms | population | households | median_income | median_house_value | |
|---|---|---|---|---|---|---|---|---|---|
| count | 20640.000000 | 20640.000000 | 20640.000000 | 20640.000000 | 20433.000000 | 20640.000000 | 20640.000000 | 20640.000000 | 20640.000000 |
| mean | -119.569704 | 35.631861 | 28.639486 | 2635.763081 | 537.870553 | 1425.476744 | 499.539680 | 3.870671 | 206855.816909 |
| std | 2.003532 | 2.135952 | 12.585558 | 2181.615252 | 421.385070 | 1132.462122 | 382.329753 | 1.899822 | 115395.615874 |
| min | -124.350000 | 32.540000 | 1.000000 | 2.000000 | 1.000000 | 3.000000 | 1.000000 | 0.499900 | 14999.000000 |
| 25% | -121.800000 | 33.930000 | 18.000000 | 1447.750000 | 296.000000 | 787.000000 | 280.000000 | 2.563400 | 119600.000000 |
| 50% | -118.490000 | 34.260000 | 29.000000 | 2127.000000 | 435.000000 | 1166.000000 | 409.000000 | 3.534800 | 179700.000000 |
| 75% | -118.010000 | 37.710000 | 37.000000 | 3148.000000 | 647.000000 | 1725.000000 | 605.000000 | 4.743250 | 264725.000000 |
| max | -114.310000 | 41.950000 | 52.000000 | 39320.000000 | 6445.000000 | 35682.000000 | 6082.000000 | 15.000100 | 500001.000000 |
import matplotlib.pyplot as plt
%matplotlib inline # 这是IPython的内置绘图命令，PyCharm用不了，可以省略plt.show()
#data.hist(bins=100,figsize=(20,15),column = 'longitude') # 选一列
# 绘制直方图
data.hist(bins=50,figsize=(20,15)) # bins 代表柱子的数目，高度为覆盖宽度内取值数目之和# plt.show()
# 划分数据集与测试集
import numpy as np
# 自定义划分函数
def split_train_test(data, test_ratio):shuffled_indices = np.random.permutation(len(data)) # 将 0 ~ len(data) 随机打乱test_set_size = int(len(data) * test_ratio)test_indices = shuffled_indices[:test_set_size]train_indices = shuffled_indices[test_set_size:]return data.iloc[train_indices], data.iloc[test_indices]
train_data,test_data = my_split_train_test(data,.2)
len(train_data),len(test_data)
(16512, 4128)
from sklearn.model_selection import train_test_split
# 利用 sklean的包 切分数据集，random_state 类似 np.random.seed(42), 保证了每次运行切分出的测试集相同
train_set, test_set = train_test_split(data, test_size=0.2, random_state=42)
len(train_set),len(test_set)
(16512, 4128)
# 但是仅仅随机抽取作为测试集是不合理的，要保证测试集的数据分布跟样本一致
# 创建收入类别属性，为了服从房价中位数的分布对数据进行划分
data["income_cat"] = pd.cut(data["median_income"],bins=[0., 1.5, 3.0, 4.5, 6., np.inf],labels=[1, 2, 3, 4, 5])
# 分层抽样
from sklearn.model_selection import StratifiedShuffleSplit
split = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=42) #
for train_index, test_index in split.split(data, data["income_cat"]):strat_train_set = data.loc[train_index]strat_test_set = data.loc[test_index]
# 查看测试集数据分布比例
strat_test_set["income_cat"].value_counts() / len(strat_test_set),data["income_cat"].value_counts() / len(data)
(3 0.3505332 0.3187984 0.1763575 0.1143411 0.039971Name: income_cat, dtype: float64,3 0.3505812 0.3188474 0.1763085 0.1144381 0.039826Name: income_cat, dtype: float64)
# 删除添加的 income_cat 属性
strat_test_set.drop("income_cat",axis=1,inplace=True)
strat_train_set.drop("income_cat",axis=1,inplace=True)
# 或者如此删除，可能效率更高，或者更美观吧
for set_ in (strat_train_set, strat_test_set):set_.drop("income_cat", axis=1, inplace=True)
