[FSTORE-1129] Tutorials Update

advanced_tutorials/air_quality/1_air_quality_feature_backfill.ipynb

@@ -576,7 +576,6 @@
     "    description='Air Quality characteristics of each day',\n",
     "    version=1,\n",
     "    primary_key=['unix_time','city_name'],\n",
-    "    online_enabled=False,\n",
     "    event_time=[\"unix_time\"],\n",
     ")    "
    ]
@@ -613,7 +612,6 @@
     "    description='Weather characteristics of each day',\n",
     "    version=1,\n",
     "    primary_key=['unix_time','city_name'],\n",
-    "    online_enabled=False,\n",
     "    event_time=[\"unix_time\"],\n",
     ") "
    ]

advanced_tutorials/air_quality/3_air_quality_training_pipeline.ipynb

@@ -128,8 +128,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Build a query object with selected features for training dataset\n",
-    "query = air_quality_fg.select_all().join(\n",
+    "# Select features for training data.\n",
+    "selected_features = air_quality_fg.select_all().join(\n",
     "    weather_fg.select_except(['unix_time']), \n",
     "    on=['city_name', 'date'],\n",
     ")"
@@ -145,22 +145,8 @@
    },
    "outputs": [],
    "source": [
-    "# here you can check out the merged dataframe\n",
-    "\n",
-    "# query_df = query.read()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0e582de6-09aa-4160-be66-0cdd831783d2",
-   "metadata": {
-    "scrolled": true,
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# query_df.city_name.value_counts()"
+    "# Uncomment this if you would like to view your selected features\n",
+    "# selected_features.show(5)"
    ]
   },
   {
@@ -198,7 +184,7 @@
     "feature_view = fs.get_or_create_feature_view(\n",
     "    name='air_quality_fv',\n",
     "    version=1,\n",
-    "    query=query,\n",
+    "    query=selected_features,\n",
     ")"
    ]
   },

advanced_tutorials/citibike/3_citibike_training_pipeline.ipynb

@@ -97,11 +97,6 @@
     "    version=1,\n",
     ")\n",
     "\n",
-    "citibike_stations_info_fg = fs.get_or_create_feature_group(\n",
-    "    name=\"citibike_stations_info\",\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
     "us_holidays_fg = fs.get_or_create_feature_group(\n",
     "    name=\"us_holidays\",\n",
     "    version=1,\n",
@@ -138,8 +133,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Select features for training data.\n",
-    "query = meteorological_measurements_fg.select_except([\"timestamp\"])\\\n",
+    "# Select features for training data\n",
+    "selected_features = meteorological_measurements_fg.select_except([\"timestamp\"])\\\n",
     "                          .join(\n",
     "                                us_holidays_fg.select_except([\"timestamp\"]),\n",
     "                                on=\"date\", join_type=\"left\"\n",
@@ -159,10 +154,8 @@
    },
    "outputs": [],
    "source": [
-    "# # uncomment and run cell below if you want to see some rows from this query\n",
-    "# # but you will have to wait some time\n",
-    "\n",
-    "# query.read()"
+    "# Uncomment this if you would like to view your selected features\n",
+    "# selected_features.show(5)"
    ]
   },
   {
@@ -198,7 +191,7 @@
    "source": [
     "feature_view = fs.get_or_create_feature_view(\n",
     "    name='citibike_fv',\n",
-    "    query=query,\n",
+    "    query=selected_features,\n",
     "    labels=[\"users_count\"],\n",
     "    version=1,   \n",
     ")"

advanced_tutorials/credit_scores/3_credit_scores_training_pipeline.ipynb

@@ -214,8 +214,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Build a query object \n",
-    "query = bureaus_fg.select_except(['sk_id_curr','sk_id_bureau','datetime'])\\\n",
+    "# Select features for training data\n",
+    "selected_features = 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",
@@ -234,8 +234,8 @@
     "            .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",
-    "query_show5 = query.show(5)\n",
-    "query_show5"
+    "selected_features_show5 = selected_features.show(5)\n",
+    "selected_features_show5"
    ]
   },
   {
@@ -284,8 +284,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Extracting the names of categorical columns in the 'query_show5' DataFrame\n",
-    "cat_cols = query_show5.dtypes[query_show5.dtypes == 'object'].index\n",
+    "# Extracting the names of categorical columns in the 'selected_features_show5query_show5' DataFrame\n",
+    "cat_cols = selected_features_show5.dtypes[selected_features_show5.dtypes == 'object'].index\n",
     "\n",
     "# Retrieving the Label Encoder transformation function from Featuretools\n",
     "le = fs.get_transformation_function(name='label_encoder') \n",
@@ -338,7 +338,7 @@
     "    version=1,\n",
     "    labels=['target'],\n",
     "    transformation_functions=transformation_functions,\n",
-    "    query=query,\n",
+    "    query=selected_features,\n",
     ")"
    ]
   },
@@ -619,7 +619,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.12"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

advanced_tutorials/electricity/3_electricity_training_pipeline.ipynb

@@ -115,7 +115,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "fg_query = electricity_prices_fg.select_all()\\\n",
+    "# Select features for training data\n",
+    "selected_features = electricity_prices_fg.select_all()\\\n",
     "    .join(\n",
     "    meteorological_measurements_fg\\\n",
     "        .select_except([\"timestamp\"])\n",
@@ -136,8 +137,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# uncomment this if you would like to view query results\n",
-    "fg_query.show(5)"
+    "# Uncomment this if you would like to view your selected features\n",
+    "# selected_features.show(5)"
    ]
   },
   {
@@ -215,7 +216,7 @@
     "    version=1,\n",
     "    labels=[], # you will define our 'y' later manualy\n",
     "    transformation_functions=mapping_transformers,\n",
-    "    query=fg_query,\n",
+    "    query=selected_features,\n",
     ")"
    ]
   },

advanced_tutorials/nyc_taxi_fares/1_nyc_taxi_fares_feature_backfill.ipynb

@@ -177,7 +177,6 @@
     "    event_time=\"pickup_datetime\",\n",
     "    description=\"Rides features\",\n",
     "    time_travel_format=\"HUDI\",     \n",
-    "    online_enabled=False,                                                \n",
     "    statistics_config=True,\n",
     ")\n",
     "\n",
@@ -208,7 +207,6 @@
     "    primary_key=[\"ride_id\"], \n",
     "    description=\"Taxi fares features\",\n",
     "    time_travel_format=\"HUDI\",  \n",
-    "    online_enabled=False,\n",
     "    statistics_config=True,\n",
     ")   \n",
     "\n",
@@ -246,7 +244,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.12"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

advanced_tutorials/nyc_taxi_fares/3_nyc_taxi_fares_training_pipeline.ipynb

@@ -107,15 +107,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Select features for training data.\n",
-    "query = fares_fg.select(['total_fare', \"tolls\"])\\\n",
+    "# Select features for training data\n",
+    "selected_features = fares_fg.select(['total_fare', \"tolls\"])\\\n",
     "                .join(rides_fg.select_except(['taxi_id', \"driver_id\", \"pickup_datetime\",\n",
     "                                              \"pickup_longitude\", \"pickup_latitude\",\n",
     "                                              \"dropoff_longitude\", \"dropoff_latitude\"]),\n",
     "                      on=['ride_id'])\n",
     "\n",
-    "# Uncomment the line below if you want to display the first 2 rows of the resulting DataFrame\n",
-    "# query.show(2)"
+    "# Uncomment this if you would like to view your selected features\n",
+    "# selected_features.show(5)"
    ]
   },
   {
@@ -151,7 +151,7 @@
     "feature_view = fs.get_or_create_feature_view(\n",
     "    name='nyc_taxi_fares_fv',\n",
     "    version=1,\n",
-    "    query=query,\n",
+    "    query=selected_features,\n",
     "    labels=[\"total_fare\"],\n",
     ")"
    ]

advanced_tutorials/recommender-system/1_feature_engineering.ipynb

@@ -6,6 +6,8 @@
    "source": [
     "## <span style=\"color:#ff5f27\">👩🏻‍🔬 Feature Engineering </span>\n",
     "\n",
+    "**Note**: This tutorial does not support Google Colab.\n",
+    "\n",
     "**Your Python Jupyter notebook should be configured for >8GB of memory.**\n",
     "\n",
     "In this series of tutorials, we will build a recommender system for fashion items. It will consist of two models: a *retrieval model* and a *ranking model*. The idea is that the retrieval model should be able to quickly generate a small subset of candidate items from a large collection of items. This comes at the cost of granularity, which is why we also train a ranking model that can afford to use more features than the retrieval model.\n",
@@ -31,59 +33,6 @@
     "## <span style=\"color:#ff5f27\">📝 Imports </span>"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Hosted notebook environments may not have the local features package\n",
-    "import os\n",
-    "\n",
-    "def need_download_modules():\n",
-    "    if 'google.colab' in str(get_ipython()):\n",
-    "        return True\n",
-    "    if 'HOPSWORKS_PROJECT_ID' in os.environ:\n",
-    "        return True\n",
-    "    return False\n",
-    "\n",
-    "if need_download_modules():\n",
-    "    print(\"⚙️ Downloading modules...\")\n",
-    "    os.system('mkdir -p features')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/articles.py')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/customers.py')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/transactions.py')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/ranking.py')        \n",
-    "    print('✅ Done!')\n",
-    "else:\n",
-    "    print(\"Local environment\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "try:\n",
-    "    from features.articles import prepare_articles\n",
-    "    from features.customers import prepare_customers\n",
-    "    from features.transactions import prepare_transactions\n",
-    "    from features.ranking import compute_ranking_dataset\n",
-    "except ImportError:\n",
-    "    print(\"⚙️ Downloading modules...\")\n",
-    "    os.system('mkdir -p features')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/articles.py')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/customers.py')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/transactions.py')\n",
-    "    os.system('cd features && wget https://raw.githubusercontent.com/logicalclocks/hopsworks-tutorials/master/advanced_tutorials/recommender-system/features/ranking.py')    \n",
-    "    print('✅ Done!')\n",
-    "    from features.articles import prepare_articles\n",
-    "    from features.customers import prepare_customers\n",
-    "    from features.transactions import prepare_transactions\n",
-    "    from features.ranking import compute_ranking_dataset    "
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -94,7 +43,12 @@
     "import numpy as np\n",
     "\n",
     "import great_expectations as ge\n",
-    "from great_expectations.core import ExpectationSuite, ExpectationConfiguration"
+    "from great_expectations.core import ExpectationSuite, ExpectationConfiguration\n",
+    "\n",
+    "from features.articles import prepare_articles\n",
+    "from features.customers import prepare_customers\n",
+    "from features.transactions import prepare_transactions\n",
+    "from features.ranking import compute_ranking_dataset  "
    ]
   },
   {
@@ -613,7 +567,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ranking_df = compute_ranking_dataset(trans_fg, articles_fg, customers_fg)"
+    "ranking_df = compute_ranking_dataset(\n",
+    "    trans_fg, \n",
+    "    articles_fg, \n",
+    "    customers_fg,\n",
+    ")"
    ]
   },
   {
@@ -687,7 +645,7 @@
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   },
   "kernelspec": {
-   "display_name": "Python",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -701,9 +659,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}