import streamlit as st
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# Load your data
train = pd.read_csv("Training.csv")
test = pd.read_csv("Testing.csv")

# Data preprocessing
train = train.drop(["Unnamed: 133"], axis=1)

# Splitting the dataset into features and target
X = train.drop(["prognosis"], axis=1)
Y = test.drop(["prognosis"], axis=1)
P = train[["prognosis"]]

# Splitting data for training and testing
x_train, x_test, y_train, y_test = train_test_split(X, P, test_size=0.2, random_state=42)

# Initialize and train classifier
model_rf = RandomForestClassifier(random_state=42)
model_rf.fit(x_train, y_train.values.ravel())

# Predictions
train_preds = model_rf.predict(x_train)
test_preds = model_rf.predict(x_test)

# Streamlit user interface
st.title('Disease Prediction App')
st.write('This app uses a machine learning model to predict diseases based on symptoms.')

# Display accuracies
st.write("Training Accuracy: ", accuracy_score(y_train, train_preds))
st.write("Testing Accuracy: ", accuracy_score(y_test, test_preds))

# User input features form
input_data = {}
for feature in X.columns:
    input_data[feature] = st.number_input('Enter value for {}:'.format(feature), min_value=0, max_value=1)

# Prediction
if st.button('Predict'):
    input_df = pd.DataFrame([input_data])
    prediction = model_rf.predict(input_df)
    st.write('Predicted Disease:', prediction[0])