4.0 release

Author: Maxxx-zh

advanced_tutorials/air_quality/1_air_quality_feature_backfill.ipynb

@@ -1131,7 +1131,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1145,7 +1145,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.8.18"
   }
  },
  "nbformat": 4,

advanced_tutorials/aml/2_aml_training_pipeline.ipynb

@@ -151,16 +151,16 @@
     "min_max_scaler = fs.get_transformation_function(name=\"min_max_scaler\")\n",
     "\n",
     "# Map features to transformations.\n",
-    "transformation_functions = {\n",
-    "    \"monthly_in_count\": min_max_scaler,\n",
-    "    \"monthly_in_total_amount\": min_max_scaler,\n",
-    "    \"monthly_in_mean_amount\": min_max_scaler,\n",
-    "    \"monthly_in_std_amount\": min_max_scaler,\n",
-    "    \"monthly_out_count\": min_max_scaler,\n",
-    "    \"monthly_out_total_amount\": min_max_scaler,\n",
-    "    \"monthly_out_mean_amount\": min_max_scaler,\n",
-    "    \"monthly_out_std_amount\": min_max_scaler,\n",
-    "}"
+    "transformation_functions = [\n",
+    "    min_max_scaler(\"monthly_in_count\"),\n",
+    "    min_max_scaler(\"monthly_in_total_amount\"),\n",
+    "    min_max_scaler(\"monthly_in_mean_amount\"),\n",
+    "    min_max_scaler(\"monthly_in_std_amount\"),\n",
+    "    min_max_scaler(\"monthly_out_count\"),\n",
+    "    min_max_scaler(\"monthly_out_total_amount\"),\n",
+    "    min_max_scaler(\"monthly_out_mean_amount\"),\n",
+    "    min_max_scaler(\"monthly_out_std_amount\"),\n",
+    "]"
    ]
   },
   {

advanced_tutorials/bitcoin/3_bitcoin_training_pipeline.ipynb

@@ -214,7 +214,7 @@
     "min_max_scaler = fs.get_transformation_function(name=\"min_max_scaler\")\n",
     "\n",
     "# Map features to transformation functions.\n",
-    "transformation_functions = {col: min_max_scaler for col in columns_to_transform}"
+    "transformation_functions = [min_max_scaler(col) for col in columns_to_transform]"
    ]
   },
   {
@@ -522,22 +522,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import inspect \n",
-    "# Recall that you applied transformation functions, such as min max scaler and laber encoder. \n",
-    "# Now you want to transform them back to human readable format.\n",
+    "# Initializing serving\n",
     "feature_view.init_serving(1)\n",
-    "td_transformation_functions = feature_view._single_vector_server._transformation_functions\n",
+    "\n",
+    "# Accessing the transformation functions used in the serving configuration\n",
+    "fv_transformation_functions = feature_view._vector_server.model_dependent_transformation_functions\n",
     "\n",
     "y_pred = pd.DataFrame(y_pred_scaled, columns=[\"close\"])\n",
     "\n",
-    "for feature_name in td_transformation_functions:\n",
-    "    if feature_name == \"close\":\n",
-    "        td_transformation_function = td_transformation_functions[feature_name]\n",
-    "        sig, foobar_locals = inspect.signature(td_transformation_function.transformation_fn), locals()\n",
-    "        param_dict = dict([(param.name, param.default) for param in sig.parameters.values() if param.default != inspect._empty])\n",
-    "        if td_transformation_function.name == \"min_max_scaler\":\n",
-    "            y_pred[feature_name] = y_pred[feature_name].map(lambda x: x*(param_dict[\"max_value\"]-param_dict[\"min_value\"])+param_dict[\"min_value\"])\n",
-    "            y_test[feature_name] = y_test[feature_name].map(lambda x: x*(param_dict[\"max_value\"]-param_dict[\"min_value\"])+param_dict[\"min_value\"])"
+    "for transformation_function in fv_transformation_functions:\n",
+    "    udf = transformation_function.hopsworks_udf\n",
+    "    transformation_feature = udf.transformation_features[0]\n",
+    "    transformed_feature = udf.transformation_features[0]\n",
+    "    if transformed_feature == \"close\" and udf.function_name == \"min_max_scaler\":\n",
+    "        stats = udf.transformation_statistics\n",
+    "        y_pred[transformation_feature] = y_pred[transformation_feature].map(lambda x: x*(stats.feature.max-stats.feature.min)+stats.feature.min)\n",
+    "        y_test[transformed_feature] = y_test[transformed_feature].map(lambda x: x*(stats.feature.max-stats.feature.min)+stats.feature.min)"
    ]
   },
   {
@@ -996,7 +996,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.12"
+   "version": "3.12.5"
   },
   "vscode": {
    "interpreter": {

advanced_tutorials/credit_scores/3_credit_scores_training_pipeline.ipynb

@@ -261,7 +261,7 @@
    "outputs": [],
    "source": [
     "# Retrieving the names of all available transformation functions\n",
-    "[t_func.name for t_func in fs.get_transformation_functions()]"
+    "[t_func for t_func in fs.get_transformation_functions()]"
    ]
   },
   {
@@ -290,11 +290,11 @@
     "label_encoder = fs.get_transformation_function(name='label_encoder') \n",
     "\n",
     "# Creating a dictionary of transformation functions, where each categorical column is associated with the Label Encoder\n",
-    "transformation_functions = {\n",
-    "    col: label_encoder\n",
+    "transformation_functions = [\n",
+    "    label_encoder(col)\n",
     "    for col \n",
     "    in cat_cols\n",
-    "}"
+    "]"
    ]
   },
   {

advanced_tutorials/electricity/3_electricity_training_pipeline.ipynb

@@ -163,21 +163,25 @@
     "# List of price areas\n",
     "price_areas = [\"se1\", \"se2\", \"se3\", \"se4\"]\n",
     "\n",
+    "# Retrieving transformation functions\n",
+    "min_max_scaler = fs.get_transformation_function(name=\"min_max_scaler\")\n",
+    "label_encoder = fs.get_transformation_function(name='label_encoder')\n",
+    "\n",
     "# Mapping features to their respective transformation functions\n",
-    "mapping_transformers = {}\n",
+    "transformation_functions = []\n",
     "\n",
     "# Iterate through each price area and map features to their transformation functions\n",
     "for area in price_areas:\n",
-    "    mapping_transformers[f\"price_{area}\"] = fs.get_transformation_function(name=\"min_max_scaler\")\n",
-    "    mapping_transformers[f\"mean_temp_per_day_{area}\"] = fs.get_transformation_function(name=\"min_max_scaler\")\n",
-    "    mapping_transformers[f\"mean_wind_speed_{area}\"] = fs.get_transformation_function(name=\"min_max_scaler\")\n",
-    "    mapping_transformers[f\"precipitaton_amount_{area}\"] = fs.get_transformation_function(name=\"min_max_scaler\")\n",
-    "    mapping_transformers[f\"total_sunshine_time_{area}\"] = fs.get_transformation_function(name=\"min_max_scaler\")\n",
-    "    mapping_transformers[f\"mean_cloud_perc_{area}\"] = fs.get_transformation_function(name=\"min_max_scaler\")    \n",
-    "    mapping_transformers[f\"precipitaton_type_{area}\"] = fs.get_transformation_function(name='label_encoder')\n",
+    "    transformation_functions.append(min_max_scaler(f\"price_{area}\"))\n",
+    "    transformation_functions.append(min_max_scaler(f\"mean_temp_per_day_{area}\"))\n",
+    "    transformation_functions.append(min_max_scaler(f\"mean_wind_speed_{area}\"))\n",
+    "    transformation_functions.append(min_max_scaler(f\"precipitaton_amount_{area}\"))\n",
+    "    transformation_functions.append(min_max_scaler(f\"total_sunshine_time_{area}\"))\n",
+    "    transformation_functions.append(min_max_scaler(f\"mean_cloud_perc_{area}\"))\n",
+    "    transformation_functions.append(label_encoder(f\"precipitaton_type_{area}\"))\n",
     "\n",
     "# Additional transformation for 'type_of_day'\n",
-    "mapping_transformers[\"type_of_day\"] = fs.get_transformation_function(name='label_encoder')"
+    "transformation_functions.append(label_encoder(\"type_of_day\"))"
    ]
   },
   {
@@ -215,7 +219,7 @@
     "    name='electricity_feature_view',\n",
     "    version=1,\n",
     "    labels=[], # you will define our 'y' later manualy\n",
-    "    transformation_functions=mapping_transformers,\n",
+    "    transformation_functions=transformation_functions,\n",
     "    query=selected_features,\n",
     ")"
    ]
@@ -304,9 +308,9 @@
    "outputs": [],
    "source": [
     "# Define 'y_train', 'y_val' and 'y_test'\n",
-    "y_train = X_train[[\"price_se1\", \"price_se2\", \"price_se3\", \"price_se4\"]]\n",
-    "y_val = X_val[[\"price_se1\", \"price_se2\", \"price_se3\", \"price_se4\"]]\n",
-    "y_test = X_test[[\"price_se1\", \"price_se2\", \"price_se3\", \"price_se4\"]]"
+    "y_train = X_train[[\"min_max_scaler_price_se1_\", \"min_max_scaler_price_se2_\", \"min_max_scaler_price_se3_\", \"min_max_scaler_price_se4_\"]]\n",
+    "y_val = X_val[[\"min_max_scaler_price_se1_\", \"min_max_scaler_price_se2_\", \"min_max_scaler_price_se3_\", \"min_max_scaler_price_se4_\"]]\n",
+    "y_test = X_test[[\"min_max_scaler_price_se1_\", \"min_max_scaler_price_se2_\", \"min_max_scaler_price_se3_\", \"min_max_scaler_price_se4_\"]]"
    ]
   },
   {
@@ -494,7 +498,7 @@
     "    input_width=4, \n",
     "    label_width=4, \n",
     "    shift=1, \n",
-    "    label_columns=[\"price_se1\", \"price_se2\", \"price_se3\", \"price_se4\"],\n",
+    "    label_columns=[\"min_max_scaler_price_se1_\", \"min_max_scaler_price_se2_\", \"min_max_scaler_price_se3_\", \"min_max_scaler_price_se4_\"],\n",
     ")\n",
     "\n",
     "# Displaying the WindowGenerator instance\n",
@@ -710,7 +714,7 @@
    "source": [
     "# Plotting the time series data for the 'price_se4' column\n",
     "n_step_window.plot(\n",
-    "    plot_col=\"price_se4\", \n",
+    "    plot_col=\"min_max_scaler_price_se4_\", \n",
     "    max_subplots=3, \n",
     "    model=model.predict,\n",
     ")"

advanced_tutorials/electricity/4_electricity_batch_inference.ipynb

@@ -250,7 +250,7 @@
     "feature_view.init_serving(1)\n",
     "\n",
     "# Accessing the transformation functions used in the serving configuration\n",
-    "td_transformation_functions = feature_view._batch_scoring_server._transformation_functions"
+    "fv_transformation_functions = feature_view._vector_server.model_dependent_transformation_functions"
    ]
   },
   {
@@ -268,15 +268,12 @@
     "\n",
     "# Extracting and decoding the transformation functions used in serving\n",
     "res = {}\n",
-    "for feature_name in td_transformation_functions:\n",
-    "    if feature_name in [\"price_se1\", \"price_se2\", \"price_se3\", \"price_se4\"]:\n",
-    "        td_transformation_function = td_transformation_functions[feature_name]\n",
-    "        sig, foobar_locals = inspect.signature(td_transformation_function.transformation_fn), locals()\n",
-    "        param_dict = dict([(param.name, param.default) for param in sig.parameters.values() if param.default != inspect._empty])\n",
-    "        if td_transformation_function.name == \"min_max_scaler\":\n",
-    "            preds[feature_name] = preds[feature_name].map(\n",
-    "                lambda x: x * (param_dict[\"max_value\"] - param_dict[\"min_value\"]) + param_dict[\"min_value\"]\n",
-    "                )\n",
+    "for transformation_function in fv_transformation_functions:\n",
+    "    udf = transformation_function.hopsworks_udf\n",
+    "    transformed_features = udf.transformation_features[0]\n",
+    "    if transformed_features in [\"price_se1\", \"price_se2\", \"price_se3\", \"price_se4\"] and udf.function_name == \"min_max_scaler\":\n",
+    "        stats = udf.transformation_statistics\n",
+    "        preds[transformed_features] = preds[transformed_features].map(lambda x: x*(stats.feature.max-stats.feature.min)+stats.feature.min)\n",
     "\n",
     "# Applying a transformation to reverse the sign of the decoded features\n",
     "preds = preds.apply(lambda x: -x)\n",
@@ -336,7 +333,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.12.5"
   }
  },
  "nbformat": 4,

advanced_tutorials/hospital_wait_time/2_training_pipeline.ipynb

@@ -129,7 +129,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "[f.name for f in fs.get_transformation_functions()]"
+    "[f for f in fs.get_transformation_functions()]"
    ]
   },
   {
@@ -153,11 +153,11 @@
    "source": [
     "features_category = ['gender', 'age_cat', 'blood_gp', 'underlying_disease', 'gestation', 'prior_transplant', 'if_transplanted']\n",
     "\n",
-    "transformation_functions_category = {\n",
-    "    feature_name: label_encoder\n",
+    "transformation_functions_category = [\n",
+    "    label_encoder(feature_name)\n",
     "    for feature_name\n",
     "    in features_category\n",
-    "}"
+    "]"
    ]
   },
   {
@@ -171,11 +171,11 @@
     "    'age_at_list_registration', 'dialysis_duration', 'number_prior_transplant', 'cpra', 'hla_a1', 'hla_a2', 'hla_b1', 'hla_b2', 'hla_dr1', 'hla_dr2',\n",
     "]\n",
     "\n",
-    "transformation_functions_numerical = {\n",
-    "    feature_name: standard_scaler\n",
+    "transformation_functions_numerical = [\n",
+    "    standard_scaler(feature_name)\n",
     "    for feature_name\n",
     "    in features_numerical\n",
-    "}"
+    "]"
    ]
   },
   {
@@ -185,8 +185,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Join transformation_functions_category and transformation_functions_numerical dictionaries into one\n",
-    "transformation_functions = transformation_functions_category | transformation_functions_numerical"
+    "# Join transformation_functions_category and transformation_functions_numerical lists into one\n",
+    "transformation_functions = transformation_functions_category + transformation_functions_numerical"
    ]
   },
   {

advanced_tutorials/on_demand_feature/notebooks/3_feature_view_td_modelling.ipynb

@@ -99,9 +99,9 @@
     "label_encoder = fs.get_transformation_function(name=\"label_encoder\")\n",
     "\n",
     "# Map features to transformation functions.\n",
-    "transformation_functions = {\n",
-    "    \"ocean_proximity\": label_encoder,\n",
-    "}"
+    "transformation_functions = [\n",
+    "    label_encoder(\"ocean_proximity\")\n",
+    "]"
    ]
   },
   {