Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,64 +1,27 @@
|
|
1 |
-
|
2 |
-
import pickle
|
3 |
import pandas as pd
|
|
|
4 |
|
5 |
-
# Load the trained
|
6 |
-
rf_fullstk = pickle.load(open('rf_hacathon_fullstk.pkl', 'rb'))
|
7 |
-
rf_prodengg = pickle.load(open('rf_hacathon_prodengg.pkl', 'rb'))
|
8 |
-
rf_mkt = pickle.load(open('rf_hacathon_mkt.pkl', 'rb'))
|
9 |
|
10 |
-
# Define the
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
'java': java,
|
17 |
-
'management': management,
|
18 |
-
'leadership': leadership,
|
19 |
-
'communication': communication,
|
20 |
-
'sales': sales
|
21 |
-
}, index=[0])
|
22 |
-
prediction = model.predict(data)[0]
|
23 |
-
probability = model.predict_proba(data)[0][1]
|
24 |
-
return prediction, probability
|
25 |
-
|
26 |
-
# Create the Streamlit app
|
27 |
-
def main():
|
28 |
-
st.title("Placement Prediction App")
|
29 |
-
st.sidebar.title("Options")
|
30 |
-
options = ["Full Stack Engineer", "Marketing", "Production Engineer"]
|
31 |
-
job_role = st.sidebar.selectbox("Select Job Role", options)
|
32 |
-
|
33 |
-
degree_p = st.slider("Degree Percentage", 0, 100, 50)
|
34 |
-
internship = st.radio("Internship", ["Yes", "No"])
|
35 |
-
DSA = st.radio("DSA Knowledge", [0, 1])
|
36 |
-
java = st.radio("Java Knowledge", [0, 1])
|
37 |
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
DSA = st.slider("DSA Knowledge", 0, 5, 0)
|
48 |
-
java = st.slider("Java Knowledge", 0, 5, 0)
|
49 |
-
prediction, probability = predict_placement(degree_p, internship, DSA, java, management, leadership, communication, sales, rf_mkt)
|
50 |
-
elif job_role == "Production Engineer":
|
51 |
-
communication = st.slider("Communication Skills", 0, 5, 0)
|
52 |
-
sales = st.slider("Sales Skills", 0, 5, 0)
|
53 |
-
management = st.slider("Management Skills", 0, 5, 0)
|
54 |
-
leadership = st.slider("Leadership Skills", 0, 5, 0)
|
55 |
-
prediction, probability = predict_placement(degree_p, internship, DSA, java, management, leadership, communication, sales, rf_prodengg)
|
56 |
-
|
57 |
-
if prediction == 1:
|
58 |
-
st.success("Placed")
|
59 |
-
st.success(f"You will be placed with a probability of {probability:.2f}")
|
60 |
-
else:
|
61 |
-
st.warning("Not Placed")
|
62 |
|
63 |
-
|
64 |
-
|
|
|
|
|
|
1 |
+
mport streamlit as st
|
|
|
2 |
import pandas as pd
|
3 |
+
import joblib
|
4 |
|
5 |
+
# Load the pre-trained model
|
|
|
|
|
|
|
6 |
|
7 |
+
# Define the input widgets
|
8 |
+
age = st.slider('Age', 18, 99, 25)
|
9 |
+
gender = st.selectbox('Gender', ['Male', 'Female'])
|
10 |
+
smoker = st.selectbox('Smoker', ['Yes', 'No'])
|
11 |
+
region = st.selectbox('Region', ['Northeast', 'Northwest', 'Southeast', 'Southwest'])
|
12 |
+
bmi = st.number_input('BMI', min_value=10.0, max_value=50.0, step=0.1)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
+
# Define a function to make the prediction
|
15 |
+
def predict(age, gender, smoker, region, bmi):
|
16 |
+
data = pd.DataFrame({'age': [age],
|
17 |
+
'sex': [gender],
|
18 |
+
'smoker': [smoker],
|
19 |
+
'region': [region],
|
20 |
+
'bmi': [bmi]})
|
21 |
+
prediction = model.predict(data)[0]
|
22 |
+
return prediction
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
+
# Call the predict function and display the result
|
25 |
+
if st.button('Predict'):
|
26 |
+
result = predict(age, gender, smoker, region, bmi)
|
27 |
+
st.write('The predicted insurance cost is $', round(result, 2))
|