Final updates

notebooks/modeling.ipynb

@@ -545,9 +545,13 @@
           "text": [
             "/Users/raymondpan/zephyr/Zephyr-repo/venv/lib/python3.8/site-packages/sklearn/impute/_base.py:555: UserWarning: Skipping features without any observed values: [ 1  2  6  7  9 10 15 16 17 18]. At least one non-missing value is needed for imputation with strategy='mean'.\n",
             "  warnings.warn(\n",
-            "[GUIDE] Successfully performed set_feature_matrix.\n",
+            "[GUIDE] STALE WARNING: set_feature_matrix.\n",
+            "\tPerforming step 2 with set_feature_matrix.\n",
+            "\tThis is a forward step via a set method.\n",
+            "\tAll previous steps' results will be considered stale.\n",
+            "[GUIDE] DONE: set_feature_matrix.\n",
             "\tYou can perform the next step by calling generate_train_test_split.\n",
-            "[GUIDE] Successfully performed generate_train_test_split.\n",
+            "[GUIDE] DONE: generate_train_test_split.\n",
             "\tYou can perform the next step by calling fit_pipeline.\n"
           ]
         },
@@ -604,7 +608,16 @@
       "execution_count": 3,
       "id": "edffee03",
       "metadata": {},
-      "outputs": [],
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "[GUIDE] DONE: fit_pipeline.\n",
+            "\tYou can perform the next step by calling predict or evaluate.\n"
+          ]
+        }
+      ],
       "source": [
         "hyperparameters = {\n",
         "    \"xgboost.XGBClassifier#1\": {\n",
@@ -629,6 +642,15 @@
       "id": "78187756",
       "metadata": {},
       "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "[GUIDE] DONE: predict.\n",
+            "\tYou have reached the end of the predictive engineering workflow.\n",
+            "\tYou can call predict or evaluate again or re-perform previous steps based on results.\n"
+          ]
+        },
         {
           "data": {
             "text/plain": [
@@ -644,6 +666,14 @@
         "zephyr.predict()"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "0c8440ee",
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    },
     {
       "cell_type": "markdown",
       "id": "24cda971",
@@ -657,7 +687,17 @@
       "execution_count": 5,
       "id": "cd097853",
       "metadata": {},
-      "outputs": [],
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "[GUIDE] DONE: evaluate.\n",
+            "\tYou have reached the end of the predictive engineering workflow.\n",
+            "\tYou can call predict or evaluate again or re-perform previous steps based on results.\n"
+          ]
+        }
+      ],
       "source": [
         "res = zephyr.evaluate()"
       ]
@@ -675,10 +715,10 @@
               " 'sklearn.metrics.precision_score': 0.5,\n",
               " 'sklearn.metrics.f1_score': 0.6666666666666666,\n",
               " 'sklearn.metrics.recall_score': 1.0,\n",
-              " 'zephyr_ml.primitives.postprocessing.confusion_matrix': (array([[1, 1],\n",
+              " 'zephyr_ml.primitives.evaluation.confusion_matrix': (array([[1, 1],\n",
               "         [0, 1]]),\n",
               "  <Figure size 640x480 with 2 Axes>),\n",
-              " 'zephyr_ml.primitives.postprocessing.roc_auc_score_and_curve': (0.5,\n",
+              " 'zephyr_ml.primitives.evaluation.roc_auc_score_and_curve': (0.5,\n",
               "  <Figure size 640x480 with 1 Axes>)}"
             ]
           },
@@ -719,13 +759,13 @@
       ],
       "source": [
         "%matplotlib inline\n",
-        "_, conf_matrix_fig = res[\"zephyr_ml.primitives.postprocessing.confusion_matrix\"]\n",
+        "_, conf_matrix_fig = res[\"zephyr_ml.primitives.evaluation.confusion_matrix\"]\n",
         "conf_matrix_fig"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 8,
+      "execution_count": 9,
       "id": "d59e86b1",
       "metadata": {},
       "outputs": [
@@ -736,17 +776,25 @@
               "<Figure size 640x480 with 1 Axes>"
             ]
           },
-          "execution_count": 8,
+          "execution_count": 9,
           "metadata": {},
           "output_type": "execute_result"
         }
       ],
       "source": [
         "\n",
-        "_, roc_fig = res[\"zephyr_ml.primitives.postprocessing.roc_auc_score_and_curve\"]\n",
+        "_, roc_fig = res[\"zephyr_ml.primitives.evaluation.roc_auc_score_and_curve\"]\n",
         "\n",
         "roc_fig\n"
       ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "38d109a1",
+      "metadata": {},
+      "outputs": [],
+      "source": []
     }
   ],
   "metadata": {

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.0.5.dev9
+current_version = 0.0.5.dev10
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?

setup.py

@@ -124,6 +124,6 @@
     test_suite='tests',
     tests_require=tests_require,
     url='https://github.com/sintel-dev/zephyr',
-    version='0.0.5.dev9',
+    version='0.0.5.dev10',
     zip_safe=False,
 )

tests/labeling/test_data_labeler.py

@@ -2,7 +2,7 @@
 
 import featuretools as ft
 
-from zephyr_ml.labeling import DataLabeler
+from zephyr_ml._labeling.data_labeler import DataLabeler
 
 
 class TestDataLabeler:

tests/labeling/test_helpers.py

@@ -2,7 +2,7 @@
 import numpy as np
 import pandas as pd
 
-from zephyr_ml.labeling.utils import (
+from zephyr_ml._labeling.utils import (
     aggregate_by_column, categorical_presence, denormalize, greater_than, keyword_in_text,
     merge_binary_labeling_functions, total_duration)
 

tests/test_entityset.py

@@ -1,7 +1,7 @@
 import pandas as pd
 import pytest
 
-from zephyr_ml import _create_entityset
+from zephyr_ml._entityset import create_entityset
 
 
 @pytest.fixture
@@ -120,11 +120,11 @@ def scada_dfs(base_dfs):
 
 
 def create_pidata_entityset(pidata_dfs):
-    return _create_entityset(pidata_dfs, es_type="pidata")
+    return create_entityset(pidata_dfs, es_type="pidata")
 
 
 def create_scada_entityset(scada_dfs):
-    return _create_entityset(scada_dfs, es_type="scada")
+    return create_entityset(scada_dfs, es_type="scada")
 
 
 def test_create_pidata_missing_entities(pidata_dfs):

tests/test_feature_engineering.py

@@ -1,8 +1,8 @@
 import pandas as pd
 import pytest
 
-from zephyr_ml import _create_entityset
-from zephyr_ml.feature_engineering import process_signals
+from zephyr_ml._entityset import create_entityset
+from zephyr_ml._feature_engineering import process_signals
 
 
 @pytest.fixture
@@ -122,12 +122,12 @@ def scada_dfs(base_dfs):
 
 @pytest.fixture
 def pidata_es(pidata_dfs):
-    return _create_entityset(pidata_dfs, "pidata")
+    return create_entityset(pidata_dfs, "pidata")
 
 
 @pytest.fixture
 def scada_es(scada_dfs):
-    return _create_entityset(scada_dfs, "scada")
+    return create_entityset(scada_dfs, "scada")
 
 
 @pytest.fixture
@@ -153,8 +153,8 @@ def test_process_signals_pidata(pidata_es, transformations, aggregations):
     replace_dataframe = False
     before = pidata_es['pidata'].copy()
 
-    process_signals(pidata_es, signal_dataframe_name, signal_column, transformations, aggregations,
-                    window_size, replace_dataframe)
+    process_signals(pidata_es, signal_dataframe_name, signal_column, transformations,
+                    aggregations, window_size, replace_dataframe)
 
     processed = pidata_es['pidata_processed'].copy()
     after = pidata_es['pidata'].copy()
@@ -189,8 +189,8 @@ def test_process_signals_pidata_replace(
     window_size = '1m'
     replace_dataframe = True
 
-    process_signals(pidata_es, signal_dataframe_name, signal_column, transformations, aggregations,
-                    window_size, replace_dataframe)
+    process_signals(pidata_es, signal_dataframe_name, signal_column, transformations,
+                    aggregations, window_size, replace_dataframe)
 
     processed = pidata_es['pidata'].copy()
 
@@ -224,8 +224,8 @@ def test_process_signals_scada(scada_es, transformations, aggregations):
     replace_dataframe = False
     before = scada_es['scada'].copy()
 
-    process_signals(scada_es, signal_dataframe_name, signal_column, transformations, aggregations,
-                    window_size, replace_dataframe)
+    process_signals(scada_es, signal_dataframe_name, signal_column, transformations,
+                    aggregations, window_size, replace_dataframe)
 
     expected = pd.DataFrame({
         "_index": [0, 1, 2],
@@ -256,8 +256,8 @@ def test_process_signals_scada_replace(
     window_size = '1m'
     replace_dataframe = True
 
-    process_signals(scada_es, signal_dataframe_name, signal_column, transformations, aggregations,
-                    window_size, replace_dataframe)
+    process_signals(scada_es, signal_dataframe_name, signal_column, transformations,
+                    aggregations, window_size, replace_dataframe)
 
     expected = pd.DataFrame({
         "_index": [0, 1, 2],

tests/test_guide.py

@@ -1,4 +1,4 @@
-from zephyr_ml.core import GuideHandler, guide
+from zephyr_ml._guide_handler import GuideHandler, guide
 
 
 class DummyObject:

tests/test_metadata.py

@@ -1,6 +1,6 @@
 import pytest
 
-from zephyr_ml.metadata import DEFAULT_ES_KWARGS, DEFAULT_ES_TYPE_KWARGS, get_mapped_kwargs
+from zephyr_ml._metadata import DEFAULT_ES_KWARGS, DEFAULT_ES_TYPE_KWARGS, get_mapped_kwargs
 
 
 def test_default_scada_mapped_kwargs():

zephyr_ml/__init__.py

@@ -4,13 +4,11 @@
 
 __author__ = 'MIT Data To AI Lab'
 __email__ = 'dai-lab@mit.edu'
-__version__ = '0.0.5.dev9'
+__version__ = '0.0.5.dev10'
 
 import os
 
 from zephyr_ml.core import Zephyr
-from zephyr_ml.entityset import VALIDATE_DATA_FUNCTIONS, _create_entityset
-from zephyr_ml.labeling import DataLabeler
 
 MLBLOCKS_PRIMITIVES = os.path.join(
     os.path.dirname(__file__), "primitives", "jsons")

zephyr_ml/entityset.py → zephyr_ml/_entityset.py

@@ -2,7 +2,7 @@
 
 import featuretools as ft
 
-from zephyr_ml.metadata import get_mapped_kwargs
+from zephyr_ml._metadata import get_mapped_kwargs
 
 
 def _validate_data(dfs, es_type, es_kwargs):
@@ -159,7 +159,7 @@ def validate_vibrations_data(dfs, new_kwargs_mapping=None):
 }
 
 
-def _create_entityset(entities, es_type, new_kwargs_mapping=None):
+def create_entityset(entities, es_type, new_kwargs_mapping=None):
 
     validate_func = VALIDATE_DATA_FUNCTIONS[es_type]
     es_kwargs = validate_func(entities, new_kwargs_mapping)