Argthtjtr

I followed this website here https://stackabuse.com/text-classification-with-python-and-scikit-learn/ and have successfully completed the model and saved it using my own data, however I don't know how to test a new document on the model. I have a bunch of documents in a string format like so: string = "Whatever and more of whatever" and I just need to know what code I need to run to test these documents through my model. My code is the exact same as the website with the only difference being the files I have loaded and to solve my problem I tried to use classifier.predict(string) and it gave me the error ValueError: could not convert string to float. Any help would be appreciated.

import re

import nltk

from sklearn.datasets import load_files

from sklearn.ensemble import RandomForestClassifier

from sklearn.feature_extraction.text import CountVectorizer

from sklearn.feature_extraction.text import TfidfTransformer

from sklearn.model_selection import train_test_split

nltk.download('wordnet')

from nltk.stem.wordnet import WordNetLemmatizer

stemmer = WordNetLemmatizer()

nltk.download('stopwords')

import pickle

from nltk.corpus import stopwords



doctor_data = load_files(r"pathtodata")

X, y = doctor_data.data, doctor_data.target



documents = 

for sen in range(0, len(X)):

    # Remove all the special characters

    document = re.sub(r'W', ' ', str(X[sen]))



    # remove all single characters

    document = re.sub(r's+[a-zA-Z]s+', ' ', document)



    # Remove single characters from the start

    document = re.sub(r'^[a-zA-Z]s+', ' ', document)



    # Substituting multiple spaces with single space

    document = re.sub(r's+', ' ', document, flags=re.I)



    # Removing prefixed 'b'

    document = re.sub(r'^bs+', '', document)



    # Converting to Lowercase

    document = document.lower()



    # Lemmatization

    document = document.split()



    document = [stemmer.lemmatize(word) for word in document]

    document = ' '.join(document)



    documents.append(document)



vectorizer = CountVectorizer(max_features=1500, min_df=5, max_df=0.7, stop_words=stopwords.words('english'))

X = vectorizer.fit_transform(documents).toarray()



tfidfconverter = TfidfTransformer()

X = tfidfconverter.fit_transform(X).toarray()



X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)



classifier = RandomForestClassifier(n_estimators=1000, random_state=0)

classifier.fit(X_train, y_train)



y_pred = classifier.predict(X_test)



from sklearn.metrics import classification_report, confusion_matrix, accuracy_score



print(confusion_matrix(y_test,y_pred))

print(classification_report(y_test,y_pred))

print(accuracy_score(y_test, y_pred))

with open('text_classifier', 'wb') as picklefile:

    pickle.dump(classifier,picklefile)

Update:
I tried to convert my document to the proper format using this code

vectorizer = CountVectorizer(max_features=1500, min_df=5, max_df=0.7, stop_words=stopwords.words('english'))

X = vectorizer.fit_transform(MYDOC).toarray()



tfidfconverter = TfidfTransformer()

X = tfidfconverter.fit_transform(X).toarray()



pred = model.predict(X)

print(pred)

And this is the error I got
ValueError: Number of features of the model must match the input. Model n_features is 897 and input n_features is 149