Upload 4 files

Startups.csv

@@ -0,0 +1,51 @@
+R&D Spend,Administration,Marketing Spend,State,Profit
+165349.2,136897.8,471784.1,New York,192261.83
+162597.7,151377.59,443898.53,California,191792.06
+153441.51,101145.55,407934.54,Florida,191050.39
+144372.41,118671.85,383199.62,New York,182901.99
+142107.34,91391.77,366168.42,Florida,166187.94
+131876.9,99814.71,362861.36,New York,156991.12
+134615.46,147198.87,127716.82,California,156122.51
+130298.13,145530.06,323876.68,Florida,155752.6
+120542.52,148718.95,311613.29,New York,152211.77
+123334.88,108679.17,304981.62,California,149759.96
+101913.08,110594.11,229160.95,Florida,146121.95
+100671.96,91790.61,249744.55,California,144259.4
+93863.75,127320.38,249839.44,Florida,141585.52
+91992.39,135495.07,252664.93,California,134307.35
+119943.24,156547.42,256512.92,Florida,132602.65
+114523.61,122616.84,261776.23,New York,129917.04
+78013.11,121597.55,264346.06,California,126992.93
+94657.16,145077.58,282574.31,New York,125370.37
+91749.16,114175.79,294919.57,Florida,124266.9
+86419.7,153514.11,0,New York,122776.86
+76253.86,113867.3,298664.47,California,118474.03
+78389.47,153773.43,299737.29,New York,111313.02
+73994.56,122782.75,303319.26,Florida,110352.25
+67532.53,105751.03,304768.73,Florida,108733.99
+77044.01,99281.34,140574.81,New York,108552.04
+64664.71,139553.16,137962.62,California,107404.34
+75328.87,144135.98,134050.07,Florida,105733.54
+72107.6,127864.55,353183.81,New York,105008.31
+66051.52,182645.56,118148.2,Florida,103282.38
+65605.48,153032.06,107138.38,New York,101004.64
+61994.48,115641.28,91131.24,Florida,99937.59
+61136.38,152701.92,88218.23,New York,97483.56
+63408.86,129219.61,46085.25,California,97427.84
+55493.95,103057.49,214634.81,Florida,96778.92
+46426.07,157693.92,210797.67,California,96712.8
+46014.02,85047.44,205517.64,New York,96479.51
+28663.76,127056.21,201126.82,Florida,90708.19
+44069.95,51283.14,197029.42,California,89949.14
+20229.59,65947.93,185265.1,New York,81229.06
+38558.51,82982.09,174999.3,California,81005.76
+28754.33,118546.05,172795.67,California,78239.91
+27892.92,84710.77,164470.71,Florida,77798.83
+23640.93,96189.63,148001.11,California,71498.49
+15505.73,127382.3,35534.17,New York,69758.98
+22177.74,154806.14,28334.72,California,65200.33
+1000.23,124153.04,1903.93,New York,64926.08
+1315.46,115816.21,297114.46,Florida,49490.75
+0,135426.92,0,California,42559.73
+542.05,51743.15,0,New York,35673.41
+0,116983.8,45173.06,California,14681.4

app.py

@@ -0,0 +1,76 @@
+import pandas as pd
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+import streamlit as st
+import joblib
+
+# Load the trained model and dataset
+model = joblib.load('best_regression_model.pkl')
+df = pd.read_csv('Startups.csv')
+
+# Preprocessor setup for scaling numerical and encoding categorical features
+preprocessor = ColumnTransformer(
+    transformers=[
+        ('num', StandardScaler(), ['R&D Spend', 'Administration', 'Marketing Spend']),
+        ('cat', OneHotEncoder(), ['State'])
+    ]
+)
+
+# Pipeline for preprocessing and model prediction
+pipeline = Pipeline(steps=[('preprocessor', preprocessor), ('regressor', model)])
+pipeline.fit(df[['R&D Spend', 'Administration', 'Marketing Spend', 'State']], df[['Profit']])
+
+# Prediction function
+def price_pred(rd, administration, marketing, state):
+    input_data = pd.DataFrame({
+        'R&D Spend': [rd],
+        'Administration': [administration],
+        'Marketing Spend': [marketing],
+        'State': [state]
+    })
+    prediction = pipeline.predict(input_data)[0]
+    return prediction
+
+# Main function for Streamlit app layout
+def main():
+    st.set_page_config(page_title="Profit Prediction", page_icon="💰", layout="wide")
+    
+    # Header Section
+    st.title("💼 Profit Prediction Tool")
+    st.markdown("""
+    Welcome to the **Profit Prediction Tool**! This tool uses machine learning to predict the profit of a company 
+    based on different financial parameters. Please input the values for **R&D Spend**, **Administration Spend**, 
+    and **Marketing Spend** along with the **State** to get the predicted profit.
+    """)
+    
+    # Sidebar Section for better organization
+    st.sidebar.header("Enter Your Company Details")
+    state = st.sidebar.selectbox('Select your State', df['State'].unique())
+    rd = st.sidebar.number_input('R&D Spend Amount ($)', 0, int(df['R&D Spend'].max()), step=1000)
+    administration = st.sidebar.number_input('Administration Spend Amount ($)', 0, int(df['Administration'].max()), step=1000)
+    marketing = st.sidebar.number_input('Marketing Spend Amount ($)', 0, int(df['Marketing Spend'].max()), step=1000)
+
+    # Display entered data for user confirmation
+    st.markdown("### You entered:")
+    st.write(f"**State**: {state}")
+    st.write(f"**R&D Spend**: ${rd:,.2f}")
+    st.write(f"**Administration Spend**: ${administration:,.2f}")
+    st.write(f"**Marketing Spend**: ${marketing:,.2f}")
+    
+    # Prediction Button
+    if st.sidebar.button('Predict Profit'):
+        profit = price_pred(rd, administration, marketing, state)
+        profit = float(profit)
+        st.markdown(f"### The Predicted Profit is: **${profit:,.2f}**")
+    
+    # Add some styling with markdown and display information
+    st.markdown("""
+    ---
+    ### About the Model
+    The model is built using a **regression algorithm** that takes into account the R&D spend, administration expenses, 
+    and marketing spend for a company to predict its profit. The model was trained using real-world company data.
+    """)
+
+if __name__ == '__main__':
+    main()

best_regression_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1a197dc6c1c7a0c03998e4f615650f5f33a647c681655f86cdbbf2744f563a
+size 178493

requirements.txt

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