add code to calculate df

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 finalized_model.sav filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

app.py

@@ -17,7 +17,8 @@ iface = gr.Interface(
             gr.inputs.Dropdown(choices=room_list, type="value", default=None, label='Room')
         ], 
     outputs= [
-            gr.outputs.Textbox(type="text", label='Predicted House Price ($)')
+            gr.Textbox(type="text", label='Predicted House Price ($)'),
+            gr.Dataframe(row_count = (10, "dynamic"), col_count=(4, "fixed"), label="Past transactions")
         ]
     )
 iface.launch()

main.py

@@ -7,6 +7,29 @@ import pandas as pd
 import datetime
 from datetime import datetime
 
+def findlast10(postal):
+    df = pd.read_json("data/data_features.json", lines=True)
+    df_filtered = df[df['Postal']==str(postal)]
+
+    df_output=df_filtered.sort_values(by='transaction_yr', ascending=False).head(10).reset_index(drop=True)
+
+    storey_dict = {
+        '01 TO 03': 1, '04 TO 06': 2, '07 TO 09': 3, '10 TO 12': 4,
+        '13 TO 15': 5, '16 TO 18': 6, '19 TO 21': 7, '22 TO 24': 8,
+        '25 TO 27': 9, '28 TO 30': 10, '31 TO 33': 11, '34 TO 36': 12,
+        '37 TO 39': 13, '40 TO 42': 14, '43 TO 45': 15, '46 TO 48': 16,
+        '49 TO 51': 17
+    }
+
+    # Swap keys and values using dictionary comprehension
+    swapped_dict = {value: key for key, value in storey_dict.items()}
+
+    df_output['storey_height']=df_output['storey_height'].apply(lambda x: swapped_dict[x])
+    df_out = df_output[['transaction','area','storey_height','resale_price']]
+
+    return df_out
+
+
 def main_fn(Postal_,age_,town_,storey_,room_):
     #Load model
     filename = 'finalized_model2.sav'
@@ -91,9 +114,12 @@ def main_fn(Postal_,age_,town_,storey_,room_):
     RPI = float(RPI_dict[formatted_quarter])
     price = resale_adj_price*(RPI/133.9) 
 
-    return int(price)
+    # Obtain the last 10 transactions with the same postal address
+    df = findlast10(Postal_input)
+
+    return (int(price), df)
 
 if __name__ == "__main__":
     Postal_,age_,town_,storey_,room_ = 680705, 30, 'CHOA CHU KANG', 12, '5 ROOM'
-    price = main_fn(Postal_,age_,town_,storey_,room_)
-    print(price)
+    item = main_fn(Postal_,age_,town_,storey_,room_)
+    print(item)

src_retired/sample.py

@@ -0,0 +1,32 @@
+import json
+import requests
+from misc import nearest_mrt
+import time
+import pickle
+import os
+import pandas as pd
+
+
+filename = 'finalized_model.sav'
+
+if os.path.exists("./finalized_model.sav"):
+    model = pickle.load(open(filename, 'rb'))
+    print('loaded model')
+else:
+    print('failed loading model')
+
+#extract feature names#
+feature_names = model.feature_names
+
+
+
+site_names = feature_names[5:31]
+town = []
+for town1 in site_names:
+    town1 = town1[5:]
+    town.append(town1)
+
+print(town)
+
+print(len(town))
+print(len(feature_names))

test.ipynb

@@ -402,6 +402,160 @@
     "price = resale_adj_price*(RPI/133.9) \n",
     "price"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "05a4a4c1-cbe7-4623-ace3-2b6c61f1575c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "686ef72d-5f24-4ed9-bf0f-4fcbc5b3138a",
+   "metadata": {},
+   "source": [
+    "## Find last 10 as dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "id": "7e9134ec-a778-4ca7-accf-4f500c1a493b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>transaction</th>\n",
+       "      <th>area</th>\n",
+       "      <th>storey_height</th>\n",
+       "      <th>resale_price</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2023-04</td>\n",
+       "      <td>114.0</td>\n",
+       "      <td>07 TO 09</td>\n",
+       "      <td>510000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2022-06</td>\n",
+       "      <td>132.0</td>\n",
+       "      <td>10 TO 12</td>\n",
+       "      <td>585000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2022-12</td>\n",
+       "      <td>109.0</td>\n",
+       "      <td>01 TO 03</td>\n",
+       "      <td>470000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2021-03</td>\n",
+       "      <td>121.0</td>\n",
+       "      <td>07 TO 09</td>\n",
+       "      <td>455000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2020-02</td>\n",
+       "      <td>109.0</td>\n",
+       "      <td>07 TO 09</td>\n",
+       "      <td>329000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>2019-05</td>\n",
+       "      <td>114.0</td>\n",
+       "      <td>04 TO 06</td>\n",
+       "      <td>330000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>2017-09</td>\n",
+       "      <td>109.0</td>\n",
+       "      <td>10 TO 12</td>\n",
+       "      <td>355000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  transaction   area storey_height  resale_price\n",
+       "0     2023-04  114.0      07 TO 09        510000\n",
+       "1     2022-06  132.0      10 TO 12        585000\n",
+       "2     2022-12  109.0      01 TO 03        470000\n",
+       "3     2021-03  121.0      07 TO 09        455000\n",
+       "4     2020-02  109.0      07 TO 09        329000\n",
+       "5     2019-05  114.0      04 TO 06        330000\n",
+       "6     2017-09  109.0      10 TO 12        355000"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_json(\"data/data_features.json\", lines=True)\n",
+    "\n",
+    "Postal_input= 680705\n",
+    "df_filtered = df[df['Postal']==str(Postal_input)]\n",
+    "\n",
+    "df_output=df_filtered.sort_values(by='transaction_yr', ascending=False).head(10).reset_index(drop=True)\n",
+    "\n",
+    "storey_dict = {\n",
+    "    '01 TO 03': 1, '04 TO 06': 2, '07 TO 09': 3, '10 TO 12': 4,\n",
+    "    '13 TO 15': 5, '16 TO 18': 6, '19 TO 21': 7, '22 TO 24': 8,\n",
+    "    '25 TO 27': 9, '28 TO 30': 10, '31 TO 33': 11, '34 TO 36': 12,\n",
+    "    '37 TO 39': 13, '40 TO 42': 14, '43 TO 45': 15, '46 TO 48': 16,\n",
+    "    '49 TO 51': 17\n",
+    "}\n",
+    "\n",
+    "# Swap keys and values using dictionary comprehension\n",
+    "swapped_dict = {value: key for key, value in storey_dict.items()}\n",
+    "\n",
+    "df_output['storey_height']=df_output['storey_height'].apply(lambda x: swapped_dict[x])\n",
+    "df_out = df_output[['transaction','area','storey_height','resale_price']]\n",
+    "\n",
+    "df_out"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "id": "667f879d-a891-4bf2-9f62-ffd96f3e809f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n"
+   ]
   }
  ],
  "metadata": {