ValueError: X has 1 features, but KNeighborsClassifier is expecting 1441 features as input.

[nehareddies]

Flask code

from flask import Flask, render_template, request
import pickle
from model import *
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
from sklearn import *

app = Flask(__name__)
model = pickle.load(open('dengue.pkl', 'rb'))

@app.route('/')
def home():
    return render_template('index.html')

@app.route('/predict', methods=['POST', 'GET'])
def predict():
    symptoms = str(request.form['text'])
    stop_words = set(stopwords.words('english'))
    words = word_tokenize(symptoms.lower())
    words = [word for word in words if word.isalpha() and word not in stop_words]
    preprocessed_symptoms = ' '.join(words)
    tfidf_vectorizer = TfidfVectorizer(max_features=1500) 
    symptom_tfidf = tfidf_vectorizer.fit_transform([preprocessed_symptoms]).toarray
    X_train, X_test, y_train, y_test = train_test_split(tfidf_features, labels, test_size=0.2, random_state=42)
    knn_classifier = KNeighborsClassifier(n_neighbors=5)  
    knn_classifier.fit(X_train, y_train)
    predictions = knn_classifier.predict(X_test)
    symptom_tfidf = tfidf_vectorizer.fit_transform([preprocessed_symptoms])
    result = model.predict(symptom_tfidf)  

    if result[0] == "Dengue":
        result = "You are more likely to be suffering from dengue!"
    else :
        result = "You have less chances that you are suffering from dengue but there are chances that you are suffering from", result[0]


    return render_template('index.html', result=result)

if __name__ == '__main__':
    app.run(debug=True)

[SeppeDeWinter]

Hi @nehareddies

I think you placed this issue on the wrong repository?

All the best,

Seppe