add time to models

api/models/bostadspriser-with-askingPrice-2024-01-05/metadata.json

@@ -0,0 +1 @@
+{"name": "bostadspriser-with-askingPrice", "nameWithDate": "bostadspriser-with-askingPrice-2024-01-05", "features": ["fee", "livingArea", "rooms", "runningCosts", "hasElevator", "hasBalcony", "lat", "long", "cpi", "hasHousingCooperative", "isPlot", "isWinterLeisureHouse", "isApartment", "isFarmWithForest", "isHouse", "isRowHouse", "isPairHouse", "isPairTerracedRowHouse", "isTerracedHouse", "isFarmWithoutForest", "isLeisureHouse", "isOtherHousingForm", "isFarmWithAgriculture", "age", "sinceLastRenovation", "soldYear", "soldMonth", "askingPrice"], "target": "finalPrice", "trainedAt": "2024-01-05T15:01:59.314123"}

api/models/bostadspriser-without-askingPrice-2024-01-05/metadata.json

@@ -0,0 +1 @@
+{"name": "bostadspriser-without-askingPrice", "nameWithDate": "bostadspriser-without-askingPrice-2024-01-05", "features": ["fee", "livingArea", "rooms", "runningCosts", "hasElevator", "hasBalcony", "lat", "long", "cpi", "hasHousingCooperative", "isPlot", "isWinterLeisureHouse", "isApartment", "isFarmWithForest", "isHouse", "isRowHouse", "isPairHouse", "isPairTerracedRowHouse", "isTerracedHouse", "isFarmWithoutForest", "isLeisureHouse", "isOtherHousingForm", "isFarmWithAgriculture", "age", "sinceLastRenovation", "soldYear", "soldMonth"], "target": "finalPrice", "trainedAt": "2024-01-05T15:01:52.948934"}

api/server.py

@@ -108,21 +108,12 @@ def predict():
     # Chose model depending on the parameters
     model = helpers.choose_model(transformed_params.keys())
 
-    print("model chosen: " + model["name"])
-
     # Convert to df and sort alphabetically
     transformed_params_df = pd.DataFrame([transformed_params])
-
-    print("before sort")
-    print(transformed_params_df.columns)
-
     transformed_params_df = transformed_params_df.reindex(
         sorted(transformed_params_df.columns), axis=1
     )
 
-    print("after sort")
-    print(transformed_params_df.columns)
-
     # Scale the data
     transformed_params = model["scaler"].transform(transformed_params_df)
 

frontend/src/api/api.js

@@ -1,5 +1,5 @@
-const api_url = "https://bostadspriser-api.app.cloud.cbh.kth.se";
-// const api_url = "http://localhost:8080";
+// const api_url = "https://bostadspriser-api.app.cloud.cbh.kth.se";
+const api_url = "http://localhost:8080";
 
 export const getListings = async (n, skip) => {
   if (n === undefined) {

model/train.py

@@ -1,10 +1,11 @@
 import sys
 import os
 import json
+import datetime
+import pickle
 
 import pandas as pd
 import numpy as np
-import pickle
 
 from sklearn.model_selection import train_test_split, GridSearchCV
 from sklearn.preprocessing import StandardScaler
@@ -129,7 +130,7 @@ def get_test_train_split(dataset, features, target):
     X_train, X_test, y_train, y_test = train_test_split(
         X, y, test_size=0.2, random_state=42
     )
-    
+
     scaler = StandardScaler()
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
@@ -201,6 +202,10 @@ def main():
     data = data.reindex(sorted(data.columns), axis=1)
 
     for name, setup in setups.items():
+        # Allow multiple timed versions of the same model
+        now = datetime.datetime.now()
+        name_with_date = name + "-" + now.strftime("%Y-%m-%d")
+
         print(f"[{name}] Getting test train split...")
         X_train, X_test, y_train, y_test, scaler = get_test_train_split(
             data, setup["features"], setup["target"]
@@ -224,7 +229,7 @@ def main():
         print(f"[{name}] Best model: " + best_model)
 
         print(f"[{name}] Saving model and results...")
-        folder = f"../models/{name}"
+        folder = f"../models/{name_with_date}"
 
         # Make directory
         os.makedirs(folder, exist_ok=True)
@@ -241,7 +246,13 @@ def main():
         results_df.to_csv(f"{folder}/results.csv")
 
         # Save metadata
-        metadata = {"features": setup["features"], "target": setup["target"]}
+        metadata = {
+            "name": name,
+            "nameWithDate": name_with_date,
+            "features": setup["features"],
+            "target": setup["target"],
+            "trainedAt": now.isoformat(),
+        }
         with open(f"{folder}/metadata.json", "w") as f:
             json.dump(metadata, f)
 

models/bostadspriser-with-askingPrice-2024-01-05/metadata.json

@@ -0,0 +1 @@
+{"name": "bostadspriser-with-askingPrice", "nameWithDate": "bostadspriser-with-askingPrice-2024-01-05", "features": ["fee", "livingArea", "rooms", "runningCosts", "hasElevator", "hasBalcony", "lat", "long", "cpi", "hasHousingCooperative", "isPlot", "isWinterLeisureHouse", "isApartment", "isFarmWithForest", "isHouse", "isRowHouse", "isPairHouse", "isPairTerracedRowHouse", "isTerracedHouse", "isFarmWithoutForest", "isLeisureHouse", "isOtherHousingForm", "isFarmWithAgriculture", "age", "sinceLastRenovation", "soldYear", "soldMonth", "askingPrice"], "target": "finalPrice", "trainedAt": "2024-01-05T15:01:59.314123"}

models/bostadspriser-without-askingPrice-2024-01-05/metadata.json

@@ -0,0 +1 @@
+{"name": "bostadspriser-without-askingPrice", "nameWithDate": "bostadspriser-without-askingPrice-2024-01-05", "features": ["fee", "livingArea", "rooms", "runningCosts", "hasElevator", "hasBalcony", "lat", "long", "cpi", "hasHousingCooperative", "isPlot", "isWinterLeisureHouse", "isApartment", "isFarmWithForest", "isHouse", "isRowHouse", "isPairHouse", "isPairTerracedRowHouse", "isTerracedHouse", "isFarmWithoutForest", "isLeisureHouse", "isOtherHousingForm", "isFarmWithAgriculture", "age", "sinceLastRenovation", "soldYear", "soldMonth"], "target": "finalPrice", "trainedAt": "2024-01-05T15:01:52.948934"}