from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.preprocessing import StandardScaler
from sklearn import metrics
import pandas as pd
class TextTransformer(BaseEstimator, TransformerMixin):
"""
Преобразование текстовых признаков
"""
def __init__(self, key):
self.key = key
def fit(self, X, y=None, *parg, **kwarg):
return self
def transform(self, X):
return X[self.key]
class NumberTransformer(BaseEstimator, TransformerMixin):
"""
Преобразование числовых признаков
"""
def __init__(self, key):
self.key = key
def fit(self, X, y=None):
return self
def transform(self, X):
return X[[self.key]]
def fit_predict(model, X_train, X_test, y_train, y_test):
vec_tdidf = TfidfVectorizer(ngram_range=(2,2), analyzer='word', norm='l2')
text = Pipeline([
('transformer', TextTransformer(key='clear_messages')),
('vectorizer', vec_tdidf)
])
word_numeric = Pipeline([
('transformer', NumberTransformer(key='word_count')),
('scalar', StandardScaler())
])
word_class = Pipeline([
('transformer', NumberTransformer(key='preds')),
('scalar', StandardScaler())
])
features = FeatureUnion([('Text_Feature', text),
('Num1_Feature', word_numeric),
('Num2_Feature', word_class)
])
clf = model
pipe = Pipeline([('features', features),
('clf',clf)
])
pipe_fit=pipe.fit(X_train, y_train)
preds = pipe_fit.predict(X_test)
return preds, pipe_fit