Upload app.py

app.py

@@ -1,55 +1,48 @@
 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
 
-## DISEASE PREDICTION
-#### IMPORT LIBRARIES
-train=pd.read_csv("Training.csv")
-test=pd.read_csv("Testing.csv")
-#### DATASET CHECKING
-train.head()
-test.head()
-#### DROP UNWANTED COLUMN
-train=train.drop(["Unnamed: 133"],axis=1)
-train.prognosis.value_counts()
-train.isna().sum()
-test.isna().sum()
-#### SPLITTING DATESET
+# 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"]]
-X = train.drop(["prognosis"],axis=1)
-Y = test.drop(["prognosis"],axis=1)
-from sklearn.model_selection import train_test_split
-xtrain,xtest,ytrain,ytest = train_test_split(X,P,test_size=0.2,random_state=42)
-## MODEL - RANDOM FOREST
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import accuracy_score
 
-rf= RandomForestClassifier(random_state=42)
-model_rf = rf.fit(xtrain,ytrain)
-tr_pred_rf = model_rf.predict(xtrain)
-ts_pred_rf = model_rf.predict(xtest)
+# 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)
 
-print("training accuracy is:",accuracy_score(ytrain,tr_pred_rf))
-print("testing accuracy is:",accuracy_score(ytest,ts_pred_rf))
+# Initialize and train classifier
+model_rf = RandomForestClassifier(random_state=42)
+model_rf.fit(x_train, y_train.values.ravel())
 
-# Title of the Streamlit app
-st.title('Prognosis Prediction App')
-### PREDICTIONS
-test.join(pd.DataFrame(model_rf.predict(Y),columns=["predicted"]))[["prognosis","predicted"]]
+# Predictions
+train_preds = model_rf.predict(x_train)
+test_preds = model_rf.predict(x_test)
 
-# Display a title
-st.title('Disease-Prognosis Correlation Visualization')
+# Streamlit user interface
+st.title('Disease Prediction App')
+st.write('This app uses a machine learning model to predict diseases based on symptoms.')
 
-# Calculate the correlation matrix
-corr = train.corr()
+# Display accuracies
+st.write("Training Accuracy: ", accuracy_score(y_train, train_preds))
+st.write("Testing Accuracy: ", accuracy_score(y_test, test_preds))
 
-# Create a heatmap to visualize the correlation
-plt.figure(figsize=(10, 8))
-sns.heatmap(corr, annot=True, cmap='coolwarm', fmt='.2f')
-plt.title('Correlation Matrix')
-st.pyplot()
+# 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)
 
-# Display the correlation values
-st.write("Correlation Values:")
-st.write(corr)
+# Prediction
+if st.button('Predict'):
+    input_df = pd.DataFrame([input_data])
+    prediction = model_rf.predict(input_df)
+    st.write('Predicted Disease:', prediction[0])