精通特征工程

分类变量：自动化时代的数据计数

｜

73

# 加载前10 000条点评

>>> f = open('yelp_academic_dataset_review.json')

>>> js = []

>>> for i in range(10000):

... js.append(json.loads(f.readline()))

>>> f.close()

>>> review_df = pd.DataFrame(js)

# 定义m为唯一的business_id的数量

>>> m = len(review_df.business_id.unique())

>>> m

528

>>> from sklearn.feature_extraction import FeatureHasher

>>> h = FeatureHasher(n_features=m, input_type='string')

>>> f = h.transform(review_df['business_id'])

# 散列化对特征可解释性的影响

>>> review_df['business_id'].unique().tolist()[0:5]

['vcNAWiLM4dR7D2nwwJ7nCA',

'UsFtqoBl7naz8AVUBZMjQQ',

'cE27W9VPgO88Qxe4ol6y_g',

'HZdLhv6COCleJMo7nPl-RA',

'mVHrayjG3uZ_RLHkLj-AMg'] ...