adds data for Obtain_dataset.ipynb

examples/Obtain_dataset.ipynb

@@ -45,57 +45,48 @@
        "      <th>Text</th>\n",
        "      <th>combined</th>\n",
        "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1303862400</td>\n",
-       "      <td>B001E4KFG0</td>\n",
-       "      <td>A3SGXH7AUHU8GW</td>\n",
+       "      <th>0</th>\n",
+       "      <td>1351123200</td>\n",
+       "      <td>B003XPF9BO</td>\n",
+       "      <td>A3R7JR3FMEBXQB</td>\n",
        "      <td>5</td>\n",
-       "      <td>Good Quality Dog Food</td>\n",
-       "      <td>I have bought several of the Vitality canned d...</td>\n",
-       "      <td>Title: Good Quality Dog Food; Content: I have ...</td>\n",
+       "      <td>where does one  start...and stop... with a tre...</td>\n",
+       "      <td>Wanted to save some to bring to my Chicago fam...</td>\n",
+       "      <td>Title: where does one  start...and stop... wit...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1346976000</td>\n",
-       "      <td>B00813GRG4</td>\n",
-       "      <td>A1D87F6ZCVE5NK</td>\n",
+       "      <th>1</th>\n",
+       "      <td>1351123200</td>\n",
+       "      <td>B003JK537S</td>\n",
+       "      <td>A3JBPC3WFUT5ZP</td>\n",
        "      <td>1</td>\n",
-       "      <td>Not as Advertised</td>\n",
-       "      <td>Product arrived labeled as Jumbo Salted Peanut...</td>\n",
-       "      <td>Title: Not as Advertised; Content: Product arr...</td>\n",
+       "      <td>Arrived in pieces</td>\n",
+       "      <td>Not pleased at all. When I opened the box, mos...</td>\n",
+       "      <td>Title: Arrived in pieces; Content: Not pleased...</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "          Time   ProductId          UserId  Score                Summary  \\\n",
-       "Id                                                                         \n",
-       "1   1303862400  B001E4KFG0  A3SGXH7AUHU8GW      5  Good Quality Dog Food   \n",
-       "2   1346976000  B00813GRG4  A1D87F6ZCVE5NK      1      Not as Advertised   \n",
+       "         Time   ProductId          UserId  Score  \\\n",
+       "0  1351123200  B003XPF9BO  A3R7JR3FMEBXQB      5   \n",
+       "1  1351123200  B003JK537S  A3JBPC3WFUT5ZP      1   \n",
        "\n",
-       "                                                 Text  \\\n",
-       "Id                                                      \n",
-       "1   I have bought several of the Vitality canned d...   \n",
-       "2   Product arrived labeled as Jumbo Salted Peanut...   \n",
+       "                                             Summary  \\\n",
+       "0  where does one  start...and stop... with a tre...   \n",
+       "1                                  Arrived in pieces   \n",
        "\n",
-       "                                             combined  \n",
-       "Id                                                     \n",
-       "1   Title: Good Quality Dog Food; Content: I have ...  \n",
-       "2   Title: Not as Advertised; Content: Product arr...  "
+       "                                                Text  \\\n",
+       "0  Wanted to save some to bring to my Chicago fam...   \n",
+       "1  Not pleased at all. When I opened the box, mos...   \n",
+       "\n",
+       "                                            combined  \n",
+       "0  Title: where does one  start...and stop... wit...  \n",
+       "1  Title: Arrived in pieces; Content: Not pleased...  "
       ]
      },
      "execution_count": 1,
@@ -106,7 +97,8 @@
    "source": [
     "import pandas as pd\n",
     "\n",
-    "df = pd.read_csv('input/Reviews.csv', index_col=0)\n",
+    "input_datapath = 'data/fine_food_reviews_1k.csv'  # to save space, we provide a pre-filtered dataset\n",
+    "df = pd.read_csv(input_datapath, index_col=0)\n",
     "df = df[['Time', 'ProductId', 'UserId', 'Score', 'Summary', 'Text']]\n",
     "df = df.dropna()\n",
     "df['combined'] = \"Title: \" + df.Summary.str.strip() + \"; Content: \" + df.Text.str.strip()\n",
@@ -161,16 +153,14 @@
     "# This will take just under 10 minutes\n",
     "df['babbage_similarity'] = df.combined.apply(lambda x: get_embedding(x, engine='text-similarity-babbage-001'))\n",
     "df['babbage_search'] = df.combined.apply(lambda x: get_embedding(x, engine='text-search-babbage-doc-001'))\n",
-    "df.to_csv('output/embedded_1k_reviews.csv')"
+    "df.to_csv('data/fine_food_reviews_with_embeddings_1k.csv')"
    ]
   }
  ],
  "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": {
@@ -185,7 +175,12 @@
    "pygments_lexer": "ipython3",
    "version": "3.9.9"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97"
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2