Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,83 +1,97 @@
-import streamlit as st
-import pickle
-import numpy as np
-
-# ---------------------------------------------------
-# Load the trained model
-# ---------------------------------------------------
-
-model = pickle.load(open("housing_model.pkl", "rb"))
-
-# ---------------------------------------------------
-# App title and description
-# ---------------------------------------------------
-
-st.title("🏠 House Price Estimator")
-
-st.write(
-"""
-This app estimates the value of a property in Île-de-France  
-based on a simple regression model trained on real estate data.
-"""
-)
-
-# ---------------------------------------------------
-# Sidebar inputs
-# ---------------------------------------------------
-
-st.sidebar.header("Property information")
-
-surface = st.sidebar.number_input(
-    "Surface (m²)",
-    min_value=10,
-    max_value=400,
-    value=70
-)
-
-rooms = st.sidebar.number_input(
-    "Number of rooms",
-    min_value=1,
-    max_value=10,
-    value=3
-)
-
-neighborhood_score = st.sidebar.slider(
-    "Neighborhood score",
-    min_value=1,
-    max_value=10,
-    value=5
-)
-
-# ---------------------------------------------------
-# Prediction
-# ---------------------------------------------------
-
-if st.sidebar.button("Estimate price"):
-
-    features = np.array([[surface, rooms, neighborhood_score]])
-
-    prediction = model.predict(features)
-
-    estimated_price = int(prediction[0])
-
-    st.subheader("Estimated property price")
-
-    st.success(f"{estimated_price:,.0f} €")
-
-# ---------------------------------------------------
-# Extra explanation
-# ---------------------------------------------------
-
-st.write("---")
-
-st.write(
-"""
-**Model inputs**
-
-- Surface of the property (m²)  
-- Number of rooms  
-- Neighborhood attractiveness score  
-
-The model predicts the approximate **market price** of the property.
-"""
-)
+Installing packages into ‘/usr/local/lib/R/site-library’
+(as ‘lib’ is unspecified)
+
+also installing the dependency ‘vroom’
+
+
+Warning message in install.packages(c("readr", "dplyr", "ggplot2", "corrplot")):
+“installation of package ‘ggplot2’ had non-zero exit status”
+
+Attaching package: ‘dplyr’
+
+
+The following objects are masked from ‘package:stats’:
+
+    filter, lag
+
+
+The following objects are masked from ‘package:base’:
+
+    intersect, setdiff, setequal, union
+
+
+corrplot 0.95 loaded
+
+Rows: 52820 Columns: 5
+── Column specification ────────────────────────────────────────────────────────
+Delimiter: ","
+dbl (5): price, surface, rooms, price_m2, neighborhood_score
+
+ℹ Use `spec()` to retrieve the full column specification for this data.
+ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
+[1] "Dataset loaded successfully"
+A tibble: 6 × 5
+price	surface	rooms	price_m2	neighborhood_score
+<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
+121000	69	2	1753.623	6.200
+246000	49	2	5020.408	5.015
+318050	115	6	2765.652	6.350
+163000	42	2	3880.952	6.350
+150000	93	5	1612.903	6.350
+153000	46	2	3326.087	5.935
+spc_tbl_ [52,820 × 5] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
+ $ price             : num [1:52820] 121000 246000 318050 163000 150000 ...
+ $ surface           : num [1:52820] 69 49 115 42 93 46 32 83 70 25 ...
+ $ rooms             : num [1:52820] 2 2 6 2 5 2 2 4 3 1 ...
+ $ price_m2          : num [1:52820] 1754 5020 2766 3881 1613 ...
+ $ neighborhood_score: num [1:52820] 6.2 5.02 6.35 6.35 6.35 ...
+ - attr(*, "spec")=
+  .. cols(
+  ..   price = col_double(),
+  ..   surface = col_double(),
+  ..   rooms = col_double(),
+  ..   price_m2 = col_double(),
+  ..   neighborhood_score = col_double()
+  .. )
+ - attr(*, "problems")=<externalptr> 
+     price            surface           rooms           price_m2     
+ Min.   :      1   Min.   :  1.00   Min.   : 0.000   Min.   :     0  
+ 1st Qu.: 185000   1st Qu.: 40.00   1st Qu.: 2.000   1st Qu.:  3193  
+ Median : 290000   Median : 62.00   Median : 3.000   Median :  4800  
+ Mean   : 405173   Mean   : 69.16   Mean   : 3.116   Mean   :  7332  
+ 3rd Qu.: 464598   3rd Qu.: 88.00   3rd Qu.: 4.000   3rd Qu.:  8341  
+ Max.   :2990000   Max.   :482.00   Max.   :24.000   Max.   :666667  
+ neighborhood_score
+ Min.   : 3.885    
+ 1st Qu.: 6.727    
+ Median : 7.780    
+ Mean   : 7.870    
+ 3rd Qu.: 9.290    
+ Max.   :20.504    
+
+
+
+
+
+Call:
+lm(formula = price ~ surface + rooms + neighborhood_score, data = train)
+
+Residuals:
+     Min       1Q   Median       3Q      Max 
+-1815140  -145637   -68531    35243  2767231 
+
+Coefficients:
+                     Estimate Std. Error t value Pr(>|t|)    
+(Intercept)        -467418.10   10358.66  -45.12   <2e-16 ***
+surface               4932.35      76.81   64.21   <2e-16 ***
+rooms               -29954.53    2059.06  -14.55   <2e-16 ***
+neighborhood_score   79383.79    1120.02   70.88   <2e-16 ***
+---
+Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
+
+Residual standard error: 341000 on 42252 degrees of freedom
+Multiple R-squared:  0.2284,	Adjusted R-squared:  0.2283 
+F-statistic:  4169 on 3 and 42252 DF,  p-value: < 2.2e-16
+[1] "RMSE: 339999.604607665"
+
+[1] "Model results saved successfully"