import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.preprocessing import MinMaxScaler
from sklearn.compose import ColumnTransformerdata = [[1, 3, 4, 'text', 'pos'], [9, 3, 6, 'text more', 'neg']]
data = pd.DataFrame(data, columns=['Num1', 'Num2', 'Num3', 'Text field', 'Class'])tweet_text_transformer = Pipeline(steps=[('count_vectoriser', CountVectorizer()),('tfidf', TfidfTransformer())
])numeric_transformer = Pipeline(steps=[('scaler', MinMaxScaler())
])preprocessor = ColumnTransformer(transformers=[# (name, transformer, column(s))('tweet', tweet_text_transformer, ['Text field']),('numeric', numeric_transformer, ['Num1', 'Num2', 'Num3'])
])pipeline = Pipeline(steps=[('preprocessor', preprocessor),('classifier', LinearSVC())
])X_train = data.loc[:, 'Num1':'Text field']
y_train = data['Class']
pipeline.fit(X_train, y_train)

I don't understand where this error is coming from:

ValueError: all the input array dimensions for the concatenation axis must match exactly, but along dimension 0, the array at index 0 has size 1 and the array at index 1 has size 2

Reason

The issue is in the preprocessor pipeline, The way this pipeline works is the output of tweet_text_transformer and the output of numeric_transformer are stacked horizontally, For this to successfully happen both the outputs(tweet_text_transformer and numeric_transformer) must have the same number of rows(ie: number of elements in axis 0 or dimension-0)

But when the above pipeline is executed the tweet_text_processor, though we expect it to give 2 * 2 matrix with 4 elements in reality since CountVectorizer stores the output as sparse matrix it removes any zeroes in the matrix(to save memory) this reduces the array to 2*2 matrix but with only 3 elements in it and when this to be stacked with the output of numeric_transformer it does not satisfy the above mentioned condition(since numeric transformer would have two elements in axis 0 and the twwet_text_processor would not)

Output of the explination

Solution

• Create a custom transformer which converts this sparse matrix to numpy array
• Also since there is only one column so squeeze the Pandas dataframe to convert it into Panadas Series

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.preprocessing import MinMaxScaler
from sklearn.compose import ColumnTransformerdata = [[1, 3, 4, 'text', 'pos'], [9, 3, 6, 'text more', 'neg']]
data = pd.DataFrame(data, columns=['Num1', 'Num2', 'Num3', 'Text field', 'Class'])class TweetTextProcessor(BaseEstimator, TransformerMixin):def __init__(self):self.tweet_text_transformer = Pipeline(steps=[('count_vectoriser', CountVectorizer()),('tfidf', TfidfTransformer())    ])def fit(self, X, y=None):return selfdef transform(self, X, y=None):return  self.tweet_text_transformer.fit_transform(X.squeeze()).toarray()numeric_transformer = Pipeline(steps=[('scaler', MinMaxScaler())
])preprocessor = ColumnTransformer(transformers=[('tweet', TweetTextProcessor(), ['Text field']),('numeric', numeric_transformer, ['Num1', 'Num2', 'Num3'])
])pipeline = Pipeline(steps=[('preprocessor', preprocessor),('classifier', LinearSVC())
])X_train = data.loc[:, 'Num1':'Text field']
y_train = data['Class']
pipeline.fit(X_train, y_train)

The above code should work, Let me know otherwise or if the explanation was not clear(hopefully it is)