Completes UNB-2565 - Add code to tutorial notebooks instead of suggesting copy / paste

Author: gustavocidornelas

examples/tabular-classification/documentation-tutorial/tabular-tutorial-part-1.ipynb

@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 1,
    "id": "56758c0a",
    "metadata": {},
    "outputs": [],
@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "4f69dcb3",
    "metadata": {},
    "outputs": [],
@@ -80,7 +80,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "2ed8bf11",
    "metadata": {},
    "outputs": [],
@@ -91,7 +91,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "ac811397",
    "metadata": {},
    "outputs": [
@@ -245,7 +245,7 @@
        "4       0  "
       ]
      },
-     "execution_count": 3,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -268,7 +268,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "0ccaafae",
    "metadata": {},
    "outputs": [],
@@ -292,7 +292,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "29e71531",
    "metadata": {},
    "outputs": [],
@@ -311,7 +311,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "3680efe3",
    "metadata": {},
    "outputs": [],
@@ -330,7 +330,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "0fcfef49",
    "metadata": {},
    "outputs": [],
@@ -341,7 +341,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "id": "53491eab",
    "metadata": {},
    "outputs": [
@@ -374,7 +374,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "id": "a981bc4b",
    "metadata": {},
    "outputs": [
@@ -384,7 +384,7 @@
        "GradientBoostingClassifier(random_state=42)"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -396,7 +396,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "ba829dcd",
    "metadata": {},
    "outputs": [
@@ -425,16 +425,16 @@
    "id": "eb702d1f",
    "metadata": {},
    "source": [
-    "## 5. Unbox part -- have fun creating the next few cells!\n",
+    "## 5. Unbox part!\n",
     "\n",
     "Now it's up to you! We will just compute a few important variables and concatenate the x and y, because Unbox expects a single dataframe with features and labels for the upload. \n",
     "\n",
-    "Head back to the tutorial to see how you need to fill out the next few cells."
+    "Head back to the tutorial for an explanation of next few cells."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "b1682ee4",
    "metadata": {},
    "outputs": [],
@@ -446,7 +446,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "d480f0c3",
    "metadata": {},
    "outputs": [],
@@ -461,6 +461,99 @@
    "id": "65964db9",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "# instantiating the client\n",
+    "import unboxapi\n",
+    "\n",
+    "client = unboxapi.UnboxClient('YOUR_API_KEY_HERE')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2dee6250",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# creating the project\n",
+    "from unboxapi.tasks import TaskType\n",
+    "\n",
+    "project = client.create_project(name=\"Churn prediction\",\n",
+    "                               task_type=TaskType.TabularClassification,\n",
+    "                               description=\"Evaluation of ML approaches to predict churn\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d0c680e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# uploading the dataset to the project\n",
+    "dataset = project.add_dataframe(\n",
+    "  df=validation_set,  \n",
+    "  commit_message='churn validation set for October',\n",
+    "  class_names=class_names,  \n",
+    "  label_column_name='Exited',    \n",
+    "  feature_names=feature_names,  \n",
+    "  categorical_feature_names=categorical_feature_names,  \n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b55095c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# defining the model's predict probability function\n",
+    "def predict_proba(model, input_features: np.ndarray, col_names: list, one_hot_encoder, encoders):\n",
+    "    # Pre-processing the categorical features\n",
+    "    df = pd.DataFrame(input_features, columns=col_names)\n",
+    "    encoded_df = one_hot_encoder(df, encoders)\n",
+    "    \n",
+    "    # Getting the model's predictions\n",
+    "    preds = model.predict_proba(encoded_df.to_numpy())\n",
+    "    \n",
+    "    return preds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d22d5cef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# uploading the model to the project\n",
+    "from unboxapi.models import ModelType\n",
+    "\n",
+    "model = project.add_model(\n",
+    "    function=predict_proba, \n",
+    "    model=sklearn_model,\n",
+    "    model_type=ModelType.sklearn,\n",
+    "    class_names=class_names,\n",
+    "    name='Churn Classifier',\n",
+    "    commit_message='this is my churn classification model',\n",
+    "    feature_names=feature_names,\n",
+    "    train_sample_df=training_set[:3000],\n",
+    "    train_sample_label_column_name='Exited',\n",
+    "    categorical_feature_names=categorical_feature_names,\n",
+    "    requirements_txt_file='requirements.txt',\n",
+    "    col_names=feature_names,\n",
+    "    one_hot_encoder=data_encode_one_hot,\n",
+    "    encoders=encoders,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c9a29256",
+   "metadata": {},
+   "outputs": [],
    "source": []
   }
  ],