使用管道和功能联合添加要素

Question

在下面的代码中，我使用tweeter数据集执行情绪分析。我使用执行以下过程的管道：

1）执行一些基本的文本预处理

2）将tweet文本矢量化

3）添加额外功能（文本长度）

4）分类

我想增加一个功能，这是规模化的追随者数量。我编写了一个函数，它将整个数据帧（df）作为输入，并返回一个新的数据帧，该数据帧具有一定数量的跟随者。但是，我发现在管道中添加这个过程是很有挑战性的，例如使用sklearn管道将这个特性添加到其他特性中。在

任何关于这个问题的帮助或建议都将不胜感激。在

下面的问题和代码源于Ryan的帖子：pipelines

import nltk
import re
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler

def import_data(filename,sep,eng,header = None,skiprows=1):
    #read csv
    dataset = pd.read_csv(filename,sep=sep,engine=eng,header = header,skiprows=skiprows)
    #rename columns
    dataset.columns = ['text','followers','sentiment']
    return dataset

df = import_data('apple_v3.txt','\t','python')
X, y = df.text, df.sentiment
X_train, X_test, y_train, y_test = train_test_split(X, y)

tokenizer = nltk.casual.TweetTokenizer(preserve_case=False, reduce_len=True)
count_vect = CountVectorizer(tokenizer=tokenizer.tokenize) 
classifier = LogisticRegression()

def get_scalled_followers(df):
    scaler = MinMaxScaler()
    df[['followers']] = df[['followers']].astype(float)
    df[['followers']] = scaler.fit_transform(df[['followers']])
    followers = df['followers'].values
    followers_reshaped = followers.reshape((len(followers),1))
    return df

def get_tweet_length(text):
    return len(text)
import numpy as np

def genericize_mentions(text):
    return re.sub(r'@[\w_-]+', 'thisisanatmention', text)

def reshape_a_feature_column(series):
    return np.reshape(np.asarray(series), (len(series), 1))

def pipelinize_feature(function, active=True):
    def list_comprehend_a_function(list_or_series, active=True):
        if active:
            processed = [function(i) for i in list_or_series]
            processed = reshape_a_feature_column(processed)
            return processed

        else:
            return reshape_a_feature_column(np.zeros(len(list_or_series)))

from sklearn.pipeline import FeatureUnion, Pipeline
from sklearn_helpers import pipelinize, genericize_mentions, train_test_and_evaluate


sentiment_pipeline = Pipeline([
        ('genericize_mentions', pipelinize(genericize_mentions, active=True)),
        ('features', FeatureUnion([
                    ('vectorizer', count_vect),
                    ('post_length', pipelinize_feature(get_tweet_length, active=True))
                ])),
        ('classifier', classifier)
    ])

sentiment_pipeline, confusion_matrix = train_test_and_evaluate(sentiment_pipeline, X_train, y_train, X_test, y_test)

Answer 1

您可以使用FeatureUnion组合从数据帧的不同列提取的特性。您应该将数据帧提供给管道，并使用FunctionTransformer来提取特定的列。它可能看起来像这样（我还没有运行它，可能有一些错误）

sentiment_pipeline = Pipeline([
    FeatureUnion([
      # your added feature (maybe you'll need to reshape it so ndim == 2)
      ('scaled_followers', FunctionTransformer(lambda df: get_scalled_followers(df).values,
                                               validate=False)),
      # previous features
      ('text_features', Pipeline([
        ('extractor', FunctionTransformer(lambda df: df.text.values, validate=False))
        ('genericize_mentions', pipelinize(genericize_mentions, active=True)),
        ('features', FeatureUnion([
                  ('vectorizer', count_vect),
                  ('post_length', pipelinize_feature(get_tweet_length, active=True))
        ])),
      ]))
    ]),
    ('classifier', classifier)
])


sentiment_pipeline, confusion_matrix = train_test_and_evaluate(sentiment_pipeline, df_train, y_train, df_test, y_test)

另一个解决方案不能使用Pipeline，而只是将这些特性与np.hstack一起堆叠。在

Answer 2

到目前为止，我找到的最好的解释是在下面的帖子中：pipelines

我的数据包括异构特性，下面的逐步方法很好用，而且很容易理解：

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline, FeatureUnion

#step1 - select data from dataframe and split the dataset in train and test sets

features= [c for c in df.columns.values if c  not in ['sentiment']]
numeric_features= [c for c in df.columns.values if c  not in ['text','sentiment']]
target = 'sentiment'

X_train, X_test, y_train, y_test = train_test_split(df[features], df[target], test_size=0.33, random_state=42)

#step2 - create a number selector class and text selector class. These classes allow to select specific columns from the dataframe

class NumberSelector(BaseEstimator, TransformerMixin):

    def __init__(self, key):
        self.key = key

    def fit(self, X, y=None):
        return self

    def transform(self, X):
        return X[[self.key]]

class TextSelector(BaseEstimator, TransformerMixin):

    def __init__(self, key):
        self.key = key

    def fit(self, X, y=None):
        return self

    def transform(self, X):
        return X[self.key]

#step 3 create one pipeline for the text data and one for the numerical data


text = Pipeline([
                ('selector', TextSelector(key='content')),
                ('tfidf', TfidfVectorizer( stop_words='english'))
            ])

text.fit_transform(X_train)

followers =  Pipeline([
                ('selector', NumberSelector(key='followers')),
                ('standard', MinMaxScaler())
            ])

followers.fit_transform(X_train)

#step 4 - features union

feats = FeatureUnion([('text', text), 
                      ('length', followers)])

feature_processing = Pipeline([('feats', feats)])
feature_processing.fit_transform(X_train)

# step 5 - add the classifier and predict 

pipeline = Pipeline([
    ('features',feats),
    ('classifier', SVC(kernel = 'linear', probability=True, C=1, class_weight = 'balanced'))
])

pipeline.fit(X_train, y_train)

preds = pipeline.predict(X_test)
np.mean(preds == y_test)

# step 6 use the model to predict new data not included in the test set
# in my example the pipeline expects a dataframe as an input which should have a column called 'text' and a column called 'followers'

array = [["@apple is amazing",25000]]
dfObj = pd.DataFrame(array,columns = ['text' , 'followers']) 

#prints the expected class e.g. positive or negative sentiment
print(pipeline.predict(dfObj))

#print the probability for each class
print(pipeline.predict_proba(dfObj))