onehot编码和无量纲化（归一化&标准化）方差过滤 PCA降维

# pandas进行onehot编码
import pandas as pd
df = pd.DataFrame([
    ["green","M",20,"class1"],
    ["red","L",21,"class2"],
    ["blue","XL",30,"class3"],
])
df.columns = ["color","size","weight","class label"]
df2 = pd.get_dummies(df["class label"])


# sklearn工具类进行onehot编码
from sklearn.feature_extraction import DictVectorizer
alist = [
    {"city":"beijing","temp":33},
    {"city":"GZ","temp":42},
    {"city":"SH","temp":40},
]
d = DictVectorizer(sparse=False)
feature = d.fit_transform(alist)
print(d.get_feature_names())
print(feature)

 归一化（当所有数据权重一样时使用）

# 归一化
from sklearn.preprocessing import MinMaxScaler
mm = MinMaxScaler(feature_range=(0,1))
data = [
    [90,2,10,40],
    [60,5,15,45],
    [73,3,13,45]
]
data = mm.fit_transform(data)

标准化（当数据存在巨大异常值时使用）

from sklearn.preprocessing import StandardScaler
ss=StandardScaler()
data = [
    [90,2,10,40],
    [60,5,15,45],
    [73,3,13,45]
]
data =ss.fit_transform(data)
print(data)

 

# Filter过滤式（方差过滤）
from sklearn.feature_selection import VarianceThreshold
v = VarianceThreshold(threshold=2)
a=v.fit_transform([[0,2,4,3],[0,3,7,3],[0,9,6,3]])


# PCA
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
a = pca.fit_transform([[0,2,4,3],[0,3,7,3],[0,9,6,3]])