adds data download from CDN with precomputed embeddings

examples/Regression_using_embeddings.ipynb

@@ -13,14 +13,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Babbage similarity embedding performance on 1k Amazon reviews: mse=0.38, mae=0.39\n"
+      "Babbage similarity embedding performance on 1k Amazon reviews: mse=0.39, mae=0.38\n"
      ]
     }
    ],
@@ -32,39 +32,41 @@
     "from sklearn.model_selection import train_test_split\n",
     "from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
     "\n",
-    "df = pd.read_csv('output/embedded_1k_reviews.csv')\n",
-    "df['babbage_similarity'] = df.babbage_similarity.apply(eval).apply(np.array)\n",
+    "datafile_path = \"https://cdn.openai.com/API/examples/data/fine_food_reviews_with_embeddings_1k.csv\"  # for your convenience, we precomputed the embeddings\n",
+    "df = pd.read_csv(datafile_path)\n",
+    "df[\"babbage_similarity\"] = df.babbage_similarity.apply(eval).apply(np.array)\n",
     "\n",
-    "X_train, X_test, y_train, y_test = train_test_split(list(df.babbage_similarity.values), df.Score, test_size = 0.2, random_state=42)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(list(df.babbage_similarity.values), df.Score, test_size=0.2, random_state=42)\n",
     "\n",
     "rfr = RandomForestRegressor(n_estimators=100)\n",
     "rfr.fit(X_train, y_train)\n",
     "preds = rfr.predict(X_test)\n",
     "\n",
-    "\n",
     "mse = mean_squared_error(y_test, preds)\n",
     "mae = mean_absolute_error(y_test, preds)\n",
     "\n",
-    "print(f\"Babbage similarity embedding performance on 1k Amazon reviews: mse={mse:.2f}, mae={mae:.2f}\")"
+    "print(f\"Babbage similarity embedding performance on 1k Amazon reviews: mse={mse:.2f}, mae={mae:.2f}\")\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Dummy mean prediction performance on Amazon reviews: mse=1.77, mae=1.04\n"
+      "Dummy mean prediction performance on Amazon reviews: mse=1.81, mae=1.08\n"
      ]
     }
    ],
    "source": [
     "bmse = mean_squared_error(y_test, np.repeat(y_test.mean(), len(y_test)))\n",
     "bmae = mean_absolute_error(y_test, np.repeat(y_test.mean(), len(y_test)))\n",
-    "print(f\"Dummy mean prediction performance on Amazon reviews: mse={bmse:.2f}, mae={bmae:.2f}\")"
+    "print(\n",
+    "    f\"Dummy mean prediction performance on Amazon reviews: mse={bmse:.2f}, mae={bmae:.2f}\"\n",
+    ")\n"
    ]
   },
   {
@@ -83,11 +85,9 @@
   }
  ],
  "metadata": {
-  "interpreter": {
-   "hash": "be4b5d5b73a21c599de40d6deb1129796d12dc1cc33a738f7bac13269cfcafe8"
-  },
   "kernelspec": {
-   "display_name": "Python 3.7.3 64-bit ('base': conda)",
+   "display_name": "Python 3.9.9 ('openai')",
+   "language": "python",
    "name": "python3"
   },
   "language_info": {
@@ -100,9 +100,14 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.9.9"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97"
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2