Update app.py

app.py

@@ -1,104 +1,50 @@
-# Gradio Implementation: Lenix Carter
-# License: BSD 3-Clause or CC-0
-
-import gradio as gr
 import numpy as np
-import matplotlib
-import matplotlib.pyplot as plt
-
-from sklearn import datasets
+import pandas as pd
 from sklearn.model_selection import train_test_split
-from sklearn.decomposition import PCA
-from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
-from sklearn.neighbors import KNeighborsClassifier, NeighborhoodComponentsAnalysis
-from sklearn.pipeline import make_pipeline
-from sklearn.preprocessing import StandardScaler
-
-matplotlib.use('agg')
-
-def reduce_dimensions(n_neighbors, random_state):
-    # Load Digits dataset
-    X, y = datasets.load_digits(return_X_y=True)
-    
-    # Split into train/test
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.5, stratify=y, random_state=random_state
-    )
-
-    dim = len(X[0])
-    n_classes = len(np.unique(y))
-
-    # Reduce dimension to 2 with PCA
-    pca = make_pipeline(StandardScaler(), PCA(n_components=2, random_state=random_state))
-
-    # Reduce dimension to 2 with LinearDiscriminantAnalysis
-    lda = make_pipeline(StandardScaler(), LinearDiscriminantAnalysis(n_components=2))
-
-    # Reduce dimension to 2 with NeighborhoodComponentAnalysis
-    nca = make_pipeline(
-        StandardScaler(),
-        NeighborhoodComponentsAnalysis(n_components=2, random_state=random_state),
-    )
-
-    # Use a nearest neighbor classifier to evaluate the methods
-    knn = KNeighborsClassifier(n_neighbors=n_neighbors)
-
-    # Make a list of the methods to be compared
-    dim_reduction_methods = [("PCA", pca), ("LDA", lda), ("NCA", nca)]
-
-    dim_red_graphs = []
-
-    for i, (name, model) in enumerate(dim_reduction_methods):
-        new = plt.figure()
-
-        # Fit the method's model
-        model.fit(X_train, y_train)
-
-        # Fit a nearest neighbor classifier on the embedded training set
-        knn.fit(model.transform(X_train), y_train)
-
-        # Compute the nearest neighbor accuracy on the embedded test set
-        acc_knn = knn.score(model.transform(X_test), y_test)
-
-        # Embed the data set in 2 dimensions using the fitted model
-        X_embedded = model.transform(X)
-
-        # Plot the projected points and show the evaluation score
-        plt.scatter(X_embedded[:, 0], X_embedded[:, 1], c=y, s=30, cmap="Set1")
-        plt.title(
-            "{}, KNN (k={})\nTest accuracy = {:.2f}".format(name, n_neighbors, acc_knn)
-        )
-        dim_red_graphs.append(new)
-    return dim_red_graphs
-
-title = "Dimensionality Reduction with Neighborhood Components Analysis"
-with gr.Blocks() as demo:
-    gr.Markdown(f" # {title}")
-    gr.Markdown("""
-                This example performs and displays the results of Principal Component Analysis, Linear Descriminant Analysis, and Neighborhood Component Analysis on the Digits dataset. 
-
-                The result shows that NCA produces visually meaningful clustering.
-
-                This based on the example [here](https://scikit-learn.org/stable/auto_examples/neighbors/plot_nca_dim_reduction.html#sphx-glr-auto-examples-neighbors-plot-nca-dim-reduction-py)
-                """)
-    with gr.Row():
-        n_neighbors = gr.Slider(2, 10, 3, step=1, label="Number of Neighbors for KNN")
-        random_state = gr.Slider(0, 100, 0, step=1, label="Random State")
-    with gr.Row():
-        pca_graph = gr.Plot(label="PCA")
-        lda_graph = gr.Plot(label="LDA")
-        nca_graph = gr.Plot(label="NCA")
-    n_neighbors.change(
-                       fn=reduce_dimensions,
-                       inputs=[n_neighbors, random_state],
-                       outputs=[pca_graph, lda_graph, nca_graph]
-                       )
-    random_state.change(
-                        fn=reduce_dimensions,
-                        inputs=[n_neighbors, random_state],
-                        outputs=[pca_graph, lda_graph, nca_graph]
-                        )
-
+from sklearn.linear_model import LinearRegression
+import streamlit as st
+def preprocess_data(df):
+    df.replace({'sex': {'male': 0, 'female': 1}}, inplace=True)
+    df.replace({'smoker': {'yes': 0, 'no': 1}}, inplace=True)
+    df.replace({'region': {'southeast': 0, 'southwest': 1, 'northwest': 2, 'northeast': 3}}, inplace=True)
+def calculate_bmi(weight, height):
+    if height == 0:
+        return 0
+    height_in_meters = height / 100
+    bmi = weight / (height_in_meters ** 2)
+    return bmi
+def main():
+    st.title("Medical Insurance Prediction Model")
+    st.sidebar.header('USER INPUT PARAMETERS')
+    p1 = st.sidebar.slider("Enter Your Age", 18, 100)
+    s1 = st.sidebar.selectbox("Sex", ["Male", "Female"])
+    p2 = 1 if s1 == "Male" else 0
+    weight = st.sidebar.number_input("Enter Your Weight (kg)", min_value=0.0, max_value=200.0)
+    height_feet = st.sidebar.number_input("Enter Your Height (feet)", min_value=0.0, max_value=8.0)
+    height_cm = height_feet * 30.48  
+    calculated_bmi = calculate_bmi(weight, height_cm)
+    p3_placeholder = st.sidebar.empty()
+    p3_placeholder.text(f"Calculated BMI: {round(calculated_bmi, 2)}")
+    p3 = st.sidebar.number_input("this is Your BMI Value", float(calculated_bmi), float(medical_df['bmi'].max()))
+    p4 = st.sidebar.slider("Enter Number of Children", 0, 5)
+    s2 = st.sidebar.selectbox("Smoker", ["Yes", "No"])
+    p5 = 1 if s2 == "Yes" else 0
+    region_mapping = {0: 'Southeast', 1: 'Southwest', 2: 'Northwest', 3: 'Northeast'}
+    region_options = list(region_mapping.values())  
+    p6 = st.sidebar.selectbox("Enter Your Region", region_options)
+    if st.sidebar.button('Predict'):
+        p6_numeric = list(region_mapping.keys())[list(region_mapping.values()).index(p6)]
+        input_data = np.array([p1, p2, calculated_bmi, p4, p5, p6_numeric]).reshape(1, -1)
+        prediction = lg.predict(input_data)
+        st.balloons()
+        st.success(f'Medical Insurance prediction : {round(prediction[0], 2)}')
 if __name__ == '__main__':
-    demo.launch()
-
+    csv_file_path = 'insurance.csv'  
+    medical_df = pd.read_csv(csv_file_path)
+    preprocess_data(medical_df)
+    X = medical_df.drop('charges', axis=1)
+    y = medical_df['charges']
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=2)
+    lg = LinearRegression()
+    lg.fit(X_train, y_train)
+    main()