lint

examples/Clustering.ipynb

@@ -29,12 +29,11 @@
     "import pandas as pd\n",
     "import numpy as np\n",
     "\n",
-    "\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",
+    "df[\"babbage_similarity\"] = df.babbage_similarity.apply(eval).apply(np.array)\n",
     "matrix = np.vstack(df.babbage_similarity.values)\n",
-    "matrix.shape"
+    "matrix.shape\n"
    ]
   },
   {
@@ -77,12 +76,12 @@
     "\n",
     "n_clusters = 4\n",
     "\n",
-    "kmeans = KMeans(n_clusters = n_clusters,init='k-means++',random_state=42)\n",
+    "kmeans = KMeans(n_clusters=n_clusters, init=\"k-means++\", random_state=42)\n",
     "kmeans.fit(matrix)\n",
     "labels = kmeans.labels_\n",
-    "df['Cluster'] = labels\n",
+    "df[\"Cluster\"] = labels\n",
     "\n",
-    "df.groupby('Cluster').Score.mean().sort_values()"
+    "df.groupby(\"Cluster\").Score.mean().sort_values()\n"
    ]
   },
   {
@@ -125,22 +124,24 @@
     "import matplotlib\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "tsne = TSNE(n_components=2, perplexity=15, random_state=42, init='random', learning_rate=200)\n",
+    "tsne = TSNE(\n",
+    "    n_components=2, perplexity=15, random_state=42, init=\"random\", learning_rate=200\n",
+    ")\n",
     "vis_dims2 = tsne.fit_transform(matrix)\n",
     "\n",
-    "x = [x for x,y in vis_dims2]\n",
-    "y = [y for x,y in vis_dims2]\n",
+    "x = [x for x, y in vis_dims2]\n",
+    "y = [y for x, y in vis_dims2]\n",
     "\n",
-    "for category, color in enumerate(['purple', 'green', 'red', 'blue']):\n",
-    "    xs = np.array(x)[df.Cluster==category]\n",
-    "    ys = np.array(y)[df.Cluster==category]\n",
+    "for category, color in enumerate([\"purple\", \"green\", \"red\", \"blue\"]):\n",
+    "    xs = np.array(x)[df.Cluster == category]\n",
+    "    ys = np.array(y)[df.Cluster == category]\n",
     "    plt.scatter(xs, ys, color=color, alpha=0.3)\n",
     "\n",
     "    avg_x = xs.mean()\n",
     "    avg_y = ys.mean()\n",
-    "    \n",
-    "    plt.scatter(avg_x, avg_y, marker='x', color=color, s=100)\n",
-    "plt.title(\"Clusters identified visualized in language 2d using t-SNE\")"
+    "\n",
+    "    plt.scatter(avg_x, avg_y, marker=\"x\", color=color, s=100)\n",
+    "plt.title(\"Clusters identified visualized in language 2d using t-SNE\")\n"
    ]
   },
   {
@@ -199,26 +200,32 @@
     "\n",
     "for i in range(n_clusters):\n",
     "    print(f\"Cluster {i} Theme:\", end=\" \")\n",
-    "    \n",
-    "    reviews = \"\\n\".join(df[df.Cluster == i].combined.str.replace(\"Title: \", \"\").str.replace(\"\\n\\nContent: \", \":  \").sample(rev_per_cluster, random_state=42).values)\n",
+    "\n",
+    "    reviews = \"\\n\".join(\n",
+    "        df[df.Cluster == i]\n",
+    "        .combined.str.replace(\"Title: \", \"\")\n",
+    "        .str.replace(\"\\n\\nContent: \", \":  \")\n",
+    "        .sample(rev_per_cluster, random_state=42)\n",
+    "        .values\n",
+    "    )\n",
     "    response = openai.Completion.create(\n",
     "        engine=\"davinci-instruct-beta-v3\",\n",
-    "        prompt=f\"What do the following customer reviews have in common?\\n\\nCustomer reviews:\\n\\\"\\\"\\\"\\n{reviews}\\n\\\"\\\"\\\"\\n\\nTheme:\",\n",
+    "        prompt=f'What do the following customer reviews have in common?\\n\\nCustomer reviews:\\n\"\"\"\\n{reviews}\\n\"\"\"\\n\\nTheme:',\n",
     "        temperature=0,\n",
     "        max_tokens=64,\n",
     "        top_p=1,\n",
     "        frequency_penalty=0,\n",
-    "        presence_penalty=0\n",
+    "        presence_penalty=0,\n",
     "    )\n",
-    "    print(response[\"choices\"][0][\"text\"].replace('\\n',''))\n",
+    "    print(response[\"choices\"][0][\"text\"].replace(\"\\n\", \"\"))\n",
     "\n",
-    "    sample_cluster_rows = df[df.Cluster == i].sample(rev_per_cluster, random_state=42) \n",
+    "    sample_cluster_rows = df[df.Cluster == i].sample(rev_per_cluster, random_state=42)\n",
     "    for j in range(rev_per_cluster):\n",
     "        print(sample_cluster_rows.Score.values[j], end=\", \")\n",
     "        print(sample_cluster_rows.Summary.values[j], end=\":   \")\n",
     "        print(sample_cluster_rows.Text.str[:70].values[j])\n",
-    "        \n",
-    "    print(\"-\" * 100)"
+    "\n",
+    "    print(\"-\" * 100)\n"
    ]
   },
   {
@@ -237,11 +244,9 @@
   }
  ],
  "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": {
@@ -256,7 +261,12 @@
    "pygments_lexer": "ipython3",
    "version": "3.9.9"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97"
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2