Question

我想训练和预测一个人的性别。我有两个功能'name'和'randint'，每个来自不同的Pandas专栏。我想 1）将它们组合成一个管道/功能组合。以及 2）将预测标签添加到原始pandas数据框中。虽然我收到了前一个目标的错误1）：

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegressionCV
from sklearn.cross_validation import train_test_split
from sklearn.base import TransformerMixin
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.pipeline import make_pipeline
from sklearn.pipeline import FeatureUnion
import numpy as np

clf = make_pipeline(CountVectorizer(), LogisticRegressionCV(cv=2))

data = {
    'Bruce Lee': 'Male',
    'Bruce Banner': 'Male',
    'Peter Parker': 'Male',
    'Peter Poker': 'Male',
    'Peter Springsteen': 'Male',
    'Bruce Willis': 'Male',
    'Sarah McLaughlin': 'Female',
    'Sarah Silverman': 'Female',
    'Sarah Palin': 'Female',
    'Sarah Hyland': 'Female',
    'Bruce Li': 'Male',
    'Bruce Milk': 'Male',
    'Bruce Springsteen': 'Male',
    'Bruce Willis': 'Male',
    'Sally Juice': 'Female',
    'Sarah Silverwoman': 'Female',
    'Sarah Palin': 'Female',
    'Sarah Hyland': 'Female',
    'Bruce Paul': 'Male',
    'Bruce Lame': 'Male',
    'Bruce Springsteen': 'Male',
    'Bruce Willis': 'Male',
    'Sarah Willis': 'Female',
    'Sarah Goldman': 'Female',
    'Sarah Palin': 'Female',
    'Sally Hyland': 'Female',
    'Bruce McDonald': 'Male',
    'Bruce Lane': 'Male',
    'Peter Springsteen': 'Male',
    'Bruce Willis': 'Male',
    'Sarah McLaughlin': 'Female',
    'Sarah Goldwoman': 'Female',
    'Sarah Palin': 'Female',
    'Sarah Hylie': 'Female'
    }

df = pd.DataFrame.from_dict(data, orient='index').reset_index()
df.columns = ['name', 'gender']
df['randomInt'] = np.random.choice(range(1, 6), df.shape[0])

class ExtractNames(TransformerMixin):
    def transform(self, X, *args):
        return [{'first': name.split()[0],
                 'last': name.split()[-1]}
                for name in X]

    def fit(self, *args):
        return self

class ExtractRandInt(TransformerMixin):
    def transform(self, X2, *args):
        return [{'randInt': num} for num in X2]

    def fit(self, *args):
        return self   

trans = ExtractNames()
trans2 = ExtractRandInt()
Combined = FeatureUnion([trans, trans2])

clf = make_pipeline(Combined(), DictVectorizer(), LogisticRegressionCV())
df_train, df_test = train_test_split(df, train_size=0.5, random_state=68)
clf.fit(df_train['name'], df_train['randomInt'], df_train['gender'])

错误：

Traceback (most recent call last):
  File "C:\Users\KubiK\Desktop\test5.py", line 74, in <module>
    clf = make_pipeline(Combined(), DictVectorizer(), LogisticRegressionCV())
TypeError: 'FeatureUnion' object is not callable

Answer 1

你不能在Combined对象上调用（）你可以在Classes上调用它，因为它是它们的构造函数，但在Combined对象中你没有__call__方法）所以该行必须是：

clf = make_pipeline(Combined, DictVectorizer(), LogisticRegressionCV())

使用Pipeline和Python Scikit-learn中的featureUnion将多个功能合二为一

1 个答案: