[优达 机器学习入门]课程10：特征缩放/课程11：文本学习

特征缩放

机器学习算法会受到特征缩放的影响？使用 RBF 核函数的 SVM和K-均值聚类

sklearn

from sklearn.preprocessing import MinMaxScaler
import numpy
weights = numpy.array([[115.],[140.],[175.]])
scaler = MinMaxScaler()
rescaled_weight = scaler.fit_transform(weights)
print rescaled_weight

def featureScaling(arr):
    import numpy as np
    arr = np.array(arr)
    max = np.max(arr)
    min = np.min(arr)
    new=[]
    for item in arr:
        if max != min :
            float (item)
            item =float(item-min)/(max-min)
            new.append(item)
        else:
            item=0.5
            new.append(item)
    return new
data = [115, 140, 175]
print featureScaling(data)

文本学习

##从NLTK中获取停止词

from nltk.corpus import stopwords
sw = stopwords.words('english')
len(sw)

##清除“签名文字”

words = ' '.join(words.split())

##进行 TfIdf

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(stop_words="english")
vectorizer.fit_transform(word_data)
feature_names = vectorizer.get_feature_names()
print len(feature_names)
print feature_names[34597]