Create app.py

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+import numpy as np
+import pickle
+from sklearn.preprocessing import StandardScaler
+
+model = pickle.load(open("model-2.pkl","rb"))
+
+def StandardScalerInput(user_input):
+    scaler = StandardScaler()
+    scaled_input = scaler.fit_transform(np.array(user_input).reshape(1,-1))
+    return scaled_input
+
+st.title("CANCER DETECTION APPLICATION")
+
+radius_mean = st.number_input('radius_mean', value=0.0)
+texture_mean = st.number_input('texture_mean', value=0.0)
+perimeter_mean = st.number_input('perimeter_mean', value=0.0)
+area_mean = st.number_input('area_mean', value=0.0)
+smoothness_mean = st.number_input('smoothness_mean', value=0.0)
+compactness_mean = st.number_input('compactness_mean', value=0.0)
+concavity_mean = st.number_input('concavity_mean', value=0.0)
+concave_points_mean = st.number_input('concave points_mean', value=0.0)
+symmetry_mean = st.number_input('symmetry_mean', value=0.0)
+fractal_dimension_mean = st.number_input('fractal_dimension_mean', value=0.0)
+radius_se = st.number_input('radius_se', value=0.0)
+texture_se = st.number_input('texture_se', value=0.0)
+perimeter_se = st.number_input('perimeter_se', value=0.0)
+area_se = st.number_input('area_se', value=0.0)
+smoothness_se = st.number_input('smoothness_se', value=0.0)
+compactness_se = st.number_input('compactness_se', value=0.0)
+concavity_se = st.number_input('concavity_se', value=0.0)
+concave_points_se = st.number_input('concave points_se', value=0.0)
+symmetry_se = st.number_input('symmetry_se', value=0.0)
+fractal_dimension_se = st.number_input('fractal_dimension_se', value=0.0)
+radius_worst = st.number_input('radius_worst', value=0.0)
+texture_worst = st.number_input('texture_worst', value=0.0)
+perimeter_worst = st.number_input('perimeter_worst', value=0.0)
+area_worst = st.number_input('area_worst', value=0.0)
+smoothness_worst = st.number_input('smoothness_worst', value=0.0)
+compactness_worst = st.number_input('compactness_worst', value=0.0)
+concavity_worst = st.number_input('concavity_worst', value=0.0)
+concave_points_worst = st.number_input('concave points_worst', value=0.0)
+symmetry_worst = st.number_input('symmetry_worst', value=0.0)
+fractal_dimension_worst = st.number_input('fractal_dimension_worst', value=0.0)
+
+user_input = [
+    radius_mean, texture_mean, perimeter_mean, area_mean, smoothness_mean,
+    compactness_mean, concavity_mean, concave_points_mean, symmetry_mean,
+    fractal_dimension_mean, radius_se, texture_se, perimeter_se, area_se,
+    smoothness_se, compactness_se, concavity_se, concave_points_se, symmetry_se,
+    fractal_dimension_se, radius_worst, texture_worst, perimeter_worst, area_worst,
+    smoothness_worst, compactness_worst, concavity_worst, concave_points_worst,
+    symmetry_worst, fractal_dimension_worst
+]
+
+if st.button("PREDICT"):
+    standardized_input = StandardScalerInput(user_input)
+    prediction = model.predict(standardized_input)
+
+    st.write("PREDICTION: ", 'CANCER DETECED' if prediction[0]=='M' else 'No Cancer Detected')