Upload 4 files

app.py

@@ -0,0 +1,69 @@
+import streamlit as st
+import pickle
+import numpy as np
+
+# Load the pre-trained model
+with open('model.pkl', 'rb') as file:
+    model = pickle.load(file)
+
+# Define the mapping for encoded species values   
+# Bream', 'Roach', 'Whitefish', 'Parkki', 'Perch', 'Pike', 'Smelt
+species_mapping = {
+    0: 'Bream',
+    1: 'Roach',
+    2: 'Whitefish',
+    3: 'Parkki',
+    4: 'Perch',
+    5: 'Pike',
+    6: 'Smelt',
+    # Add other species mappings as needed
+}
+
+# Create reverse mapping from species name to encoded value
+reverse_species_mapping = {v: k for k, v in species_mapping.items()}
+
+# Streamlit app
+st.title('Fish Weight Prediction')
+
+# Select box for species
+species_options = list(species_mapping.values())
+selected_species = st.selectbox('Select Species', species_options)
+
+# Convert selected species to encoded value
+species_encoded = reverse_species_mapping.get(selected_species, 0)  # Default to 0 if not found
+
+# Input fields for the user to enter data as text inputs
+length1 = st.text_input('Length1 (cm) [Range: 0.0 - 100.0]', '0.0')
+length2 = st.text_input('Length2 (cm) [Range: 0.0 - 100.0]', '0.0')
+length3 = st.text_input('Length3 (cm) [Range: 0.0 - 100.0]', '0.0')
+height = st.text_input('Height (cm) [Range: 0.0 - 30.0]', '0.0')
+width = st.text_input('Width (cm) [Range: 0.0 - 30.0]', '0.0')
+
+# Convert text inputs to floats and handle errors
+try:
+    length1 = float(length1)
+    length2 = float(length2)
+    length3 = float(length3)
+    height = float(height)
+    width = float(width)
+except ValueError:
+    st.error("Please enter valid numerical values.")
+    length1 = length2 = length3 = height = width = 0.0
+
+# Button to make prediction
+if st.button('Predict'):
+    # Prepare the input data for the model
+    input_data = np.array([[length1, length2, length3, height, width, species_encoded]])
+    
+    # Make prediction
+    predicted_weight = model.predict(input_data)
+    
+    # Display the result
+    st.write(f'The predicted weight is: {predicted_weight[0]:.2f} grams')
+
+st.markdown("""
+    <div style='text-align: center; padding: 20px;'>
+        <h4>Created by Sukhman</h4>
+        <p>This Streamlit app predicts the weight of Fish based on its features.</p>
+    </div>
+""", unsafe_allow_html=True)

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755a02b128a0bca948081fa6f8a915c41bf56c22f5c8751c3c167f3a992ba794
+size 651

requirements.txt

@@ -0,0 +1,3 @@
+scikit-learn
+streamlit
+numpy