ubra app = 30 mins, git debug = 4 hours. good shi

.gitignore

@@ -0,0 +1,5 @@
+..//
+
+venv/
+.git
+__pycache__/

README.md

@@ -1,13 +1,24 @@
 ---
+<<<<<<< HEAD
 title: Delhi Housing Price
 emoji: 🐨
 colorFrom: yellow
 colorTo: indigo
+=======
+title: 'Logistic Regression: Delhi Housing Price Prediction'
+emoji: 🏠
+colorFrom: green
+colorTo: orange
+>>>>>>> 9f2b567 (ubra app = 30 mins, git debug = 4 hours. good shi)
 sdk: streamlit
 sdk_version: 1.42.2
 app_file: app.py
 pinned: false
+<<<<<<< HEAD
 short_description: this app uses logreg to predict housing prices in delhi
+=======
+short_description: this app runs logistic regression to predict pricing
+>>>>>>> 9f2b567 (ubra app = 30 mins, git debug = 4 hours. good shi)
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,117 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
+
+# Load
+df = pd.read_csv("datasets/Delhi.csv")
+
+# Preprocess
+df = pd.get_dummies(df, columns=["Location"], drop_first=True)  # One-hot encode locations
+X = df.drop("Price", axis=1)
+y = df["Price"]
+median_price = y.median()
+
+# Train
+X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=1)
+model = LinearRegression()
+model.fit(X_train, y_train)
+y_pred = model.predict(X_val)
+
+# App
+st.title("Delhi Housing Price Prediction")
+tab1, tab2 = st.tabs(["Model Performance", "Price Predictor"])
+
+with tab1:
+    # Model Assessment
+    st.header("Model Performance")
+    
+    # Compute regression evaluation metrics
+    mae = mean_absolute_error(y_val, y_pred)
+    mse = mean_squared_error(y_val, y_pred)
+    r2 = r2_score(y_val, y_pred)
+
+    # Display regression metrics
+    st.write(f"**Mean Absolute Error (MAE):** {mae:,.2f}")
+    st.write(f"**Mean Squared Error (MSE):** {mse:,.2f}")
+    st.write(f"**R² Score:** {r2:.2f}")
+    st.divider()
+
+with tab2:
+    # User Input
+    st.header("Price Prediction")
+    col1, col2 = st.columns(2)
+    with col1:
+        area = st.slider("Area (sq. ft)", 500, 5000, 1500)
+        bedrooms = st.slider("Number of Bedrooms", 1, 6, 3)
+        is_resale = st.radio("Resale or New?", ["Resale", "New"]) == "New"
+        location = st.selectbox("Location", df.columns[df.columns.str.startswith("Location_")].str.replace("Location_", ""))
+    with col2:
+        is_swimming_pool = st.checkbox("Has Swimming Pool")
+        is_car_parking = st.checkbox("Has Car Parking")
+        is_ac = st.checkbox("Has Air Conditioning")
+        is_wifi = st.checkbox("Has Wifi")
+        is_microwave = st.checkbox("Has Microwave")
+        is_tv = st.checkbox("Has TV")
+        is_dining_table = st.checkbox("Has Dining Table")
+        is_sofa = st.checkbox("Has Sofa")
+        is_wardrobe = st.checkbox("Has Wardrobe")
+        is_refrigerator = st.checkbox("Has Refrigerator")
+        
+        # Process Input Data
+    input_data = np.zeros(len(X.columns))  # Create zero array matching feature length
+    input_data[0] = area
+    input_data[1] = bedrooms
+    input_data[2] = int(is_resale)
+    input_data[3] = int(is_swimming_pool)
+    input_data[4] = int(is_car_parking)
+    input_data[5] = int(is_ac)
+    input_data[6] = int(is_wifi)
+    input_data[7] = int(is_microwave)
+    input_data[8] = int(is_tv)
+    input_data[9] = int(is_dining_table)
+    input_data[10] = int(is_sofa)
+    input_data[11] = int(is_wardrobe)
+    input_data[12] = int(is_refrigerator)
+
+    # Set the correct location column to 1
+    loc_index = list(X.columns).index(f"Location_{location}")
+    input_data[loc_index] = 1
+
+    # Predict & Output
+    predicted_price = model.predict([input_data])[0]
+
+    # Set colors kag descs kay bigaon
+    price_diff = (predicted_price - median_price) / median_price
+    if price_diff < -0.2:
+        color = "#ff4d4d"  # Below Median
+        category = "Below Median Price"
+        description = "This price is significantly lower than the median price in this area. The property may lack premium features and amenities or be in a less desirable location."
+    elif -0.2 <= price_diff < -0.05:
+        color = "#ff944d"  # Slightly Below
+        category = "Slightly Below Median Price"
+        description = "This price is slightly below the median range, which could indicate a competitive offer for budget-conscious buyers."
+    elif -0.05 <= price_diff <= 0.05:
+        color = "#ffff4d"  # In Median Range
+        category = "In Median Price Range"
+        description = "This price falls within the typical range for this area, making it a standard market price."
+    elif 0.05 < price_diff <= 0.2:
+        color = "#94ff4d"  # Slightly Above
+        category = "Slightly Above Median Price"
+        description = "This price is slightly higher than the median, possibly due to added features such as better amenities or a prime location."
+    else:
+        color = "#4dff4d"  # Above Median
+        category = "Above Median Price"
+        description = "This price is significantly above the median, suggesting a premium property with high-end features, amenities, and an excellent location."
+
+    # Result
+    st.subheader("Predicted House Price (INR)")
+    st.write(f"₹{predicted_price:,.2f}")
+    st.markdown(f'<h3 style="color:{color};">{category}</h3>', unsafe_allow_html=True)
+    st.write(description)
+    st.caption("Dataset is small so expect anomalous output (negative prices).")
+    st.divider()

requirements.txt

@@ -0,0 +1,7 @@
+matplotlib==3.8.0
+numpy==2.2.3
+pandas==2.2.3
+scikit_learn==1.2.2
+seaborn==0.13.2
+streamlit==1.30.0
+streamlit==1.42.2