[HWORKS-850] Add event_time to all tutorials with 2 or more fgs (#218)

Add event_time to all tutorials with 2 or more fgs
logicalclocks · Nov 29, 2023 · d39d676 · d39d676
1 parent f9989b0
commit d39d676
Show file tree

Hide file tree

Showing 5 changed files with 33 additions and 7 deletions.
diff --git a/advanced_tutorials/credit_scores/1_credit_scores_feature_backfill.ipynb b/advanced_tutorials/credit_scores/1_credit_scores_feature_backfill.ipynb
@@ -413,6 +413,7 @@
     "    version=1,\n",
     "    primary_key=['sk_id_curr'],\n",
     "    online_enabled=False,\n",
+    "    event_time='datetime',\n",
     ")\n",
     "applications_fg.insert(\n",
     "    applications_df,\n",
@@ -467,6 +468,7 @@
     "    version=1,\n",
     "    primary_key=['sk_id_curr','sk_id_bureau'],\n",
     "    online_enabled=False,\n",
+    "    event_time='datetime',\n",
     ")\n",
     "bureaus_fg.insert(\n",
     "    bureaus_df,\n",
@@ -494,6 +496,7 @@
     "    version=1,\n",
     "    primary_key=['sk_id_prev','sk_id_curr'],\n",
     "    online_enabled=False,\n",
+    "    event_time='datetime',\n",
     ")\n",
     "previous_applications_fg.insert(\n",
     "    previous_applications_df,\n",
@@ -548,6 +551,7 @@
     "    version=1,\n",
     "    primary_key=['sk_id_prev','sk_id_curr'],\n",
     "    online_enabled=False,\n",
+    "    event_time='datetime',\n",
     ")\n",
     "installment_payments_fg.insert(\n",
     "    installment_payments_df,\n",

diff --git a/advanced_tutorials/credit_scores/2_credit_scores_feature_pipeline.ipynb b/advanced_tutorials/credit_scores/2_credit_scores_feature_pipeline.ipynb
@@ -29,6 +29,7 @@
    "outputs": [],
    "source": [
     "from functions import generate_data\n",
+    "from datetime import datetime\n",
     "\n",
     "#ignore warnings\n",
     "import warnings\n",
@@ -267,6 +268,18 @@
     "## <span style=\"color:#ff5f27;\"> 🧙🏼‍♂️ Data Generation </span>"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd420aa0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get today's date and time\n",
+    "today_date_time = datetime.now()\n",
+    "today_date_time"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -275,6 +288,7 @@
    "outputs": [],
    "source": [
     "applications_df_generated = generate_data(applications_df)\n",
+    "applications_df_generated['datetime'] = today_date_time\n",
     "applications_df_generated.head(3)"
    ]
   },
@@ -297,6 +311,7 @@
    "outputs": [],
    "source": [
     "bureaus_df_generated = generate_data(bureaus_df)\n",
+    "bureaus_df_generated['datetime'] = today_date_time\n",
     "bureaus_df_generated.head(3)"
    ]
   },
@@ -319,6 +334,7 @@
    "outputs": [],
    "source": [
     "installment_payments_df_generated = generate_data(installment_payments_df)\n",
+    "installment_payments_df_generated['datetime'] = today_date_time\n",
     "installment_payments_df_generated.head(3)"
    ]
   },
@@ -341,6 +357,7 @@
    "outputs": [],
    "source": [
     "previous_applications_df_generated = generate_data(previous_applications_df)\n",
+    "previous_applications_df_generated['datetime'] = today_date_time\n",
     "previous_applications_df_generated.head(3)"
    ]
   },

diff --git a/advanced_tutorials/credit_scores/3_credit_scores_training_pipeline.ipynb b/advanced_tutorials/credit_scores/3_credit_scores_training_pipeline.ipynb
@@ -215,8 +215,9 @@
    "outputs": [],
    "source": [
     "# Build a query object \n",
-    "query = bureaus_fg.select_except(['sk_id_curr','sk_id_bureau'])\\\n",
+    "query = bureaus_fg.select_except(['sk_id_curr','sk_id_bureau','datetime'])\\\n",
     "            .join(applications_fg.select_except(['sk_id_curr',\n",
+    "                                                 'datetime',\n",
     "                                                 'flag_mobil',\n",
     "                                                 *[f'flag_document_{num}'\n",
     "                                                   for num\n",
@@ -225,11 +226,11 @@
     "                                                 'amt_credit', 'weekday_appr_process_start',\n",
     "                                                 'hour_appr_process_start']))\\\n",
     "            .join(bureau_balances_fg.select_except(['sk_id_bureau','months_balance']))\\\n",
-    "            .join(previous_applications_fg.select_except(['sk_id_prev', 'sk_id_curr',\n",
+    "            .join(previous_applications_fg.select_except(['sk_id_prev', 'sk_id_curr','datetime',\n",
     "                                                          'name_contract_type', 'name_contract_status']))\\\n",
     "            .join(pos_cash_balances_fg.select_except(['sk_id_prev','sk_id_curr', 'months_balance',\n",
     "                                                      'name_contract_status', 'sk_dpd', 'sk_dpd_def']))\\\n",
-    "            .join(installment_payments_fg.select_except(['sk_id_prev', 'sk_id_curr']))\\\n",
+    "            .join(installment_payments_fg.select_except(['sk_id_prev', 'sk_id_curr', 'datetime']))\\\n",
     "            .join(credit_card_balances_fg.select_except(['sk_id_prev', 'sk_id_curr']))\\\n",
     "            .join(previous_loan_counts_fg.select_except('sk_id_curr'))\n",
     "\n",

diff --git a/churn/1_churn_feature_pipeline.ipynb b/churn/1_churn_feature_pipeline.ipynb
@@ -204,6 +204,7 @@
     "    version=1,\n",
     "    description=\"Customer info for churn prediction.\",\n",
     "    primary_key=['customerID'],\n",
+    "    event_time=\"datetime\",\n",
     ")"
    ]
   },
@@ -244,7 +245,8 @@
     "    {\"name\": \"paperlessbilling\", \"description\": \"Whether customer has paperless billing or not\"}, \n",
     "    {\"name\": \"monthlycharges\", \"description\": \"Monthly charges\"}, \n",
     "    {\"name\": \"totalcharges\", \"description\": \"Total charges\"},\n",
-    "    {\"name\": \"churn\", \"description\": \"Whether customer has left within the last month or not\"},  \n",
+    "    {\"name\": \"churn\", \"description\": \"Whether customer has left within the last month or not\"},\n",
+    "    {\"name\": \"datetime\", \"description\": \"Date when the customer information was recorded\"},\n",
     "]\n",
     "\n",
     "for desc in feature_descriptions: \n",
@@ -302,6 +304,7 @@
     "    version=1,\n",
     "    description=\"Customer subscription info for churn prediction.\",\n",
     "    primary_key=['customerID'],\n",
+    "    event_time=\"datetime\",\n",
     ")\n",
     "# Insert data into feature group\n",
     "subscriptions_fg.insert(\n",
@@ -328,7 +331,8 @@
     "    {\"name\": \"phoneservice\", \"description\": \"Whether customer has signed up for phone service\"}, \n",
     "    {\"name\": \"techsupport\", \"description\": \"Whether customer has signed up for tech support service\"}, \n",
     "    {\"name\": \"streamingmovies\", \"description\": \"Whether customer has signed up for streaming movies service\"}, \n",
-    "    {\"name\": \"streamingtv\", \"description\": \"Whether customer has signed up for streaming TV service\"}, \n",
+    "    {\"name\": \"streamingtv\", \"description\": \"Whether customer has signed up for streaming TV service\"},\n",
+    "    {\"name\": \"datetime\", \"description\": \"Date when the customer information was recorded\"},\n",
     "]\n",
     "\n",
     "for desc in feature_descriptions: \n",

diff --git a/churn/2_churn_training_pipeline.ipynb b/churn/2_churn_training_pipeline.ipynb
@@ -123,9 +123,9 @@
    "outputs": [],
    "source": [
     "# Select features for training data\n",
-    "query = customer_info_fg.select_except([\"customerid\"]) \\\n",
+    "query = customer_info_fg.select_except([\"customerid\", \"datetime\"]) \\\n",
     "    .join(demography_fg.select_except([\"customerid\"])) \\\n",
-    "    .join(subscriptions_fg.select_all())\n",
+    "    .join(subscriptions_fg.select_except([\"datetime\"]))\n",
     "\n",
     "# uncomment this if you would like to view query result\n",
     "# query.show(5)"