Improve house prices project

.gitignore

@@ -43,6 +43,7 @@ links.db
 blacklist.txt
 searchlive
 wiki_history
+house_prices.zip
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

house_prices/README.md

@@ -35,7 +35,9 @@ To follow this project, please install the following locally:
 
 ## Data
 
-You'll need to download a few csv files to run this project.  These files are included in this repo, but you may want newer versions:
+You'll need to download a few csv files to run this project.  These files are included in this repo.  You can also download them all [here](https://drive.google.com/uc?export=download&id=1HlHw_JyRckfPOlwwxUHS-sdDqfZQ732p).
+
+If you want to get newer versions:
 
 * Federal reserve data
     * [CPI dataset](https://fred.stlouisfed.org/series/CPIAUCSL) - CPIAUCSL.csv

house_prices/prices.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Files Needed\n",
     "\n",
-    "Before running this code, make sure you have these files available.  Check the README file for more info on how to get them.\n",
+    "Before running this code, make sure you have these files available.  You can get them by cloning the code repository, or downloading them [here](https://drive.google.com/uc?export=download&id=1HlHw_JyRckfPOlwwxUHS-sdDqfZQ732p).\n",
     "\n",
     "- `CPIAUCSL.csv` - US CPI (inflation measure)\n",
     "- `RRVRUSQ156N.csv` - rental vacancy rate, quarterly\n",
@@ -832,6 +832,28 @@
     "dfs[0]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c7c79d80-19e9-47dc-8699-4d78a9254860",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'dfs' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m/var/folders/xz/9z84c__j28g8tg28bmcthjj00000gn/T/ipykernel_6759/1633160854.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdfs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'dfs' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "dfs[1]"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 251,
@@ -2283,7 +2305,6 @@
     "STEP = 52\n",
     "\n",
     "def predict(train, test, predictors, target):\n",
-    "    \n",
     "    rf = RandomForestClassifier(min_samples_split=10, random_state=1)\n",
     "    rf.fit(train[predictors], train[target])\n",
     "    preds = rf.predict(test[predictors])\n",