Upload 3 files

app.py

@@ -0,0 +1,101 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import mlflow
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+import streamlit as st
+import numpy as np
+import joblib
+
+url = './archive/ds_salaries.csv'  # replace with the actual path
+
+# Load the dataset
+data = pd.read_csv(url)
+
+data = data.drop('Unnamed: 0', axis=1)
+
+
+# Fill missing values if any
+data = data.fillna(method='ffill')
+
+# Encode categorical variables
+label_encoders = {}
+categorical_columns = ['experience_level', 'employment_type', 'job_title', 'salary_currency', 'employee_residence', 'company_location', 'company_size']
+
+for col in categorical_columns:
+    le = LabelEncoder()
+    data[col] = le.fit_transform(data[col])
+    label_encoders[col] = le
+
+from sklearn.model_selection import train_test_split
+
+# Define features and target variable
+X = data.drop('salary_in_usd', axis=1)
+y = data['salary_in_usd']
+
+# Split the data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+print(f"Training set size: {X_train.shape[0]}")
+print(f"Testing set size: {X_test.shape[0]}")
+
+
+# Load the best model
+# best_model = mlflow.sklearn.load_model("runs:/2f24d11653334bfc8611ef5edbe52bfd/model")
+
+# Load the best model
+best_model = joblib.load('best_model.pkl')
+
+# Streamlit app
+st.title("Salary Prediction App")
+
+# Input features
+work_year = st.number_input('Work Year', min_value=2020, max_value=2024, step=1)
+experience_level = st.selectbox("Experience Level", label_encoders['experience_level'].classes_)
+employment_type = st.selectbox("Employment Type", label_encoders['employment_type'].classes_)
+job_title = st.selectbox("Job Title", label_encoders['job_title'].classes_)
+salary = st.number_input('Salary', min_value=0)
+salary_currency = st.selectbox("Salary Currency", label_encoders['salary_currency'].classes_)
+employee_residence = st.selectbox("Employee Residence", label_encoders['employee_residence'].classes_)
+remote_ratio = st.slider("Remote Ratio", 0, 100)
+company_location = st.selectbox("Company Location", label_encoders['company_location'].classes_)
+company_size = st.selectbox("Company Size", label_encoders['company_size'].classes_)
+
+
+def predict_salary():
+    # Encode input features
+    encoded_experience_level = label_encoders['experience_level'].transform([experience_level])[0]
+    encoded_employment_type = label_encoders['employment_type'].transform([employment_type])[0]
+    encoded_job_title = label_encoders['job_title'].transform([job_title])[0]
+    encoded_salary_currency = label_encoders['salary_currency'].transform([salary_currency])[0]
+    encoded_employee_residence = label_encoders['employee_residence'].transform([employee_residence])[0]
+    encoded_company_location = label_encoders['company_location'].transform([company_location])[0]
+    encoded_company_size = label_encoders['company_size'].transform([company_size])[0]
+
+    # Create input array matching training data format
+    input_features = np.array([
+        work_year,
+        encoded_experience_level,
+        encoded_employment_type,
+        encoded_job_title,
+        salary,
+        encoded_salary_currency,
+        encoded_employee_residence,
+        remote_ratio,
+        encoded_company_location,
+        encoded_company_size,
+    ]).reshape(1, -1)
+    # Make prediction
+    predicted_salary = best_model.predict(input_features)[0]
+    return predicted_salary
+
+# Button to trigger prediction
+if st.button("Predict Salary"):
+    predicted_salary = predict_salary()
+    st.write(f"Predicted Salary (in USD): {predicted_salary}")
+
+    # Display model performance metrics
+    st.write(f"RMSE: {mean_squared_error(y_test, best_model.predict(X_test), squared=False)}")
+    st.write(f"MAE: {mean_absolute_error(y_test, best_model.predict(X_test))}")
+    st.write(f"R²: {r2_score(y_test, best_model.predict(X_test))}")

best_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd0785ba695a9dbc50a84b1b3a4e38289f9aabb6bd39a50196349c6179a1c58
+size 5834256

requirements.txt

@@ -0,0 +1,8 @@
+mlflow==2.13.2
+cloudpickle==3.0.0
+numpy==1.24.4
+packaging==24.1
+psutil==5.9.8
+pyyaml==6.0.1
+scikit-learn==1.3.2
+scipy==1.10.1