sklearn与机器学习知识点概括

数值型变量的标准化
axis=0按列归总； axis=1按整个样本计算均值、标准差
In [1]:

1
from sklearn import datasets
2
import numpy as np
3
import pandas as pd
In [2]:

1
boston = datasets.load_boston()
2
boston_df = pd.DataFrame(boston.data, columns = boston.feature_names)
In [3]:

1
boston_df.head()
Out[3]:
CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT
0 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.0900 1.0 296.0 15.3 396.90 4.98
1 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671 2.0 242.0 17.8 396.90 9.14
2 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671 2.0 242.0 17.8 392.83 4.03
3 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622 3.0 222.0 18.7 394.63 2.94
4 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 3.0 222.0 18.7 396.90 5.33
In [4]:

1
from sklearn import preprocessing
2
boston_scaled = preprocessing.scale(boston_df)
In [5]:

1
boston_scaled
Out[5]:
array([[-0.41978194, 0.28482986, -1.2879095 , …, -1.45900038,
0.44105193, -1.0755623 ],
[-0.41733926, -0.48772236, -0.59338101, …, -0.30309415,
0.44105193, -0.49243937],
[-0.41734159, -0.48772236, -0.59338101, …, -0.30309415,
0.39642699, -1.2087274 ],
…,
[-0.41344658, -0.48772236, 0.11573841, …, 1.17646583,
0.44105193, -0.98304761],
[-0.40776407, -0.48772236, 0.11573841, …, 1.17646583,
0.4032249 , -0.86530163],
[-0.41500016, -0.48772236, 0.11573841, …, 1.17646583,
0.44105193, -0.66905833]])
In [6]:

1
boston_scaled.mean(axis = 0)
Out[6]:
array([-8.78743718e-17, -6.34319123e-16, -2.68291099e-15, 4.70199198e-16,
2.49032240e-15, -1.14523016e-14, -1.40785495e-15, 9.21090169e-16,
5.44140929e-16, -8.86861950e-16, -9.20563581e-15, 8.16310129e-15,
-3.37016317e-16])
In [7]:

1
boston_scaled.std(axis = 0)
Out[7]:
array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.])
In [10]:

1
boston_scaled_all = preprocessing.scale(boston_df,axis=1)
In [11]:

1
boston_scaled_all.mean(axis = 0)
Out[11]:
array([-0.4780112 , -0.40553476, -0.42254267, -0.49773735, -0.49427398,
-0.45178493, -0.01134041, -0.46893722, -0.43835293, 2.28303321,
-0.36385904, 2.159172 , -0.40983071])
In [12]:

1
boston_scaled_all.std(axis = 0)
Out[12]:
array([0.06425559, 0.18342798, 0.0560845 , 0.03195557, 0.03193079,
0.03022877, 0.19077168, 0.03244151, 0.06559356, 0.60447227,
0.03530255, 0.83087432, 0.05416801])
In [13]:

1
boston_scaled_all.mean(),boston_scaled_all.std()
Out[13]:
(-7.392485326631476e-18, 1.0)
In [14]:

1
preprocessing.scale(boston.target)
Out[14]:
array([ 0.15968566, -0.10152429, 1.32424667, 1.18275795, 1.48750288,
0.6712218 , 0.03996443, 0.49708184, -0.65659542, -0.39538548,
-0.81985164, -0.39538548, -0.09064054, -0.23212926, -0.47157171,
-0.286548 , 0.06173193, -0.54775795, -0.25389676, -0.47157171,
-0.97222411, -0.31919924, -0.79808414, -0.87427038, -0.75454915,
-0.93957286, -0.64571167, -0.84161913, -0.44980422, -0.16682677,
-1.07017784, -0.87427038, -1.0157591 , -1.02664285, -0.98310786,
-0.39538548, -0.27566425, -0.16682677, 0.23587189, 0.89978051,
1.34601416, 0.4426631 , 0.30117438, 0.23587189, -0.14505928,
-0.35185049, -0.27566425, -0.64571167, -0.88515413, -0.34096674,
-0.30831549, -0.22124551, 0.26852314, 0.09438317, -0.39538548,
1.4004329 , 0.23587189, 0.98685049, 0.08349942, -0.31919924,
-0.41715297, -0.71101416, -0.0362218 , 0.26852314, 1.13922296,
0.10526692, -0.34096674, -0.0579893 , -0.55864169, -0.17771052,
0.18145315, -0.09064054, 0.02908069, 0.09438317, 0.17056941,
-0.12329178, -0.27566425, -0.18859427, -0.14505928, -0.24301301,
0.59503557, 0.14880191, 0.24675564, 0.03996443, 0.14880191,
0.4426631 , -0.00357056, -0.0362218 , 0.11615067, 0.6712218 ,
0.00731319, -0.0579893 , 0.03996443, 0.26852314, -0.21036176,
0.63857056, -0.12329178, 1.75959658, 2.31466771, 1.16099045,
0.54061683, 0.43177935, -0.42803672, -0.35185049, -0.2647805 ,
-0.33008299, -0.33008299, -0.23212926, -0.29743175, -0.34096674,
-0.09064054, 0.02908069, -0.40626922, -0.41715297, -0.43892047,
-0.46068796, -0.14505928, -0.36273423, -0.23212926, -0.35185049,
-0.0579893 , -0.24301301, -0.22124551, -0.56952544, -0.40626922,
-0.12329178, -0.7436654 , -0.68924667, -0.49333921, -0.89603787,
-0.36273423, -0.31919924, 0.05084818, -0.44980422, -0.75454915,
-0.48245546, -0.55864169, -0.59129294, -1.00487535, -0.5151067 ,
-0.92868912, -0.88515413, -0.9939916 , -0.75454915, -1.16813157,
-0.95045661, -0.75454915, -0.86338663, -0.5151067 , -0.77631665,
-0.11240804, -0.31919924, -0.7872004 , -0.34096674, -0.60217668,
-0.75454915, -1.02664285, 2.04257402, 0.1923369 , 0.08349942,
0.48619809, 2.98946007, 2.98946007, 2.98946007, 0.01819694,
0.26852314, 2.98946007, 0.13791816, 0.13791816, -0.02533805,
-0.55864169, -0.37361798, 0.06173193, 0.11615067, 0.00731319,
0.74740804, 0.07261568, 0.22498815, 0.80182678, 1.59634036,
1.8793178 , 1.48750288, 1.6725266 , 1.08480422, 0.4208956 ,
0.76917553, 2.98946007, 1.03038548, 0.79094303, 1.34601416,
1.57457287, 0.86712926, 1.50927038, 0.93243175, 0.71475679,
2.98946007, 1.1718742 , 0.84536177, 1.31336292, 1.34601416,
1.12833921, 0.17056941, 2.1514115 , 2.82620386, 2.98946007,
0.00731319, 0.20322065, -0.00357056, 0.20322065, -0.27566425,
-0.09064054, -0.35185049, -0.01445431, 0.60591932, 0.12703442,
0.26852314, 0.08349942, 0.6712218 , -0.11240804, 0.05084818,
0.45354685, -0.09064054, 0.54061683, 0.82359427, 2.42350519,
2.98946007, 1.63987535, 0.98685049, 2.6302964 , 0.97596674,
0.1923369 , 0.99773424, 2.08610901, 2.80443636, 0.70387305,
0.15968566, 0.27940688, 0.97596674, 0.12703442, 0.08349942,
-0.0579893 , -0.2647805 , -0.0362218 , 0.12703442, -0.5368742 ,
-0.43892047, 0.1923369 , -0.22124551, 0.2141044 , 0.39912811,
0.20322065, 0.24675564, 0.76917553, 2.20583024, -0.06887304,
-0.17771052, 2.33643521, 2.98946007, 1.46573539, 0.82359427,
1.22629294, 2.23848148, 2.8588551 , 0.921548 , 1.52015413,
0.02908069, 0.88889676, 2.98946007, 2.28201647, -0.19947802,
-0.15594303, 0.29029063, 0.20322065, 1.37866541, 1.07392047,
1.03038548, 1.16099045, 1.1501067 , 0.71475679, 1.36778166,
2.48880768, 1.4004329 , 2.55411016, 2.98946007, 1.05215297,
-0.0579893 , -0.2647805 , 0.07261568, -0.02533805, 0.24675564,
0.64945431, 1.60722411, 0.58415182, 0.14880191, -0.09064054,
0.66033806, 0.49708184, -0.24301301, -0.00357056, 0.70387305,
0.24675564, -0.0579893 , 0.4208956 , 1.1501067 , 1.47661914,
0.63857056, 1.18275795, 0.61680306, 0.02908069, -0.24301301,
-0.70013041, -0.04710555, -0.34096674, -0.10152429, 0.13791816,
-0.68924667, -0.5151067 , -0.29743175, 0.06173193, -0.16682677,
0.13791816, 0.06173193, -0.23212926, -0.43892047, 0.26852314,
0.22498815, 0.05084818, -0.0362218 , -0.35185049, 0.00731319,
-0.29743175, -0.59129294, -0.34096674, -0.0362218 , -0.19947802,
-0.15594303, -0.33008299, -0.43892047, -0.21036176, -0.38450173,