v0.3.11 release (#74)

v0.3.11 release Features: * Traffic light overview (#62) Documentation: * Downloads badge readme * List talks and articles in readme (#66) * Add image to README.rst (#64) Other improvements: * Change notebook testing to pytest-notebook (previously these tests were skipped in CI). Add try-except ImportError for pyspark code. (#67) * Fix a few typo's * suppress "matplotlib backend" verbose warning * click on "popmon report" also scrolls to top * Update HTML reports using Github Actions (#63) * Bugfix in hist.py that broke the advanced tutorial. Notebooks: * Add %%capture to pip install inside of notebooks. * Make package install in notebooks work with paths with spaces. * Pickle doesn't work with tests (not really a popmon-specific feature anyway). Changed the notebook to fix the issue, left the code for reference. * Version bump
ing-bank · Dec 7, 2020 · b8d94a0 · b8d94a0
1 parent dd707f4
commit b8d94a0
Show file tree

Hide file tree

Showing 17 changed files with 489 additions and 137 deletions.
diff --git a/README.rst b/README.rst
@@ -2,7 +2,7 @@
 Population Shift Monitoring
 ===========================
 
-|build| |docs| |release| |release_date|
+|build| |docs| |release| |release_date| |downloads|
 
 |logo|
 
@@ -128,6 +128,37 @@ These examples also work with spark dataframes.
 You can see the output of such example notebook code `here <https://crclz.com/popmon/reports/test_data_report.html>`_.
 For all available examples, please see the `tutorials <https://popmon.readthedocs.io/en/latest/tutorials.html>`_ at read-the-docs.
 
+Resources
+=========
+
+Presentations
+-------------
+
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+| Title                                                                                          | Host                                                                                             | Date             | Speaker                 |
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+| Popmon - population monitoring made easy                                                       | `Data Lunch @ Eneco <https://www.eneco.nl/>`_                                                    | October 29, 2020 | Max Baak, Simon Brugman |
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+| Popmon - population monitoring made easy                                                       | `Data Science Summit 2020 <https://dssconf.pl/en/>`_                                             | October 16, 2020 | Max Baak                |
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+| `Population Shift Monitoring Made Easy: the popmon package <https://youtu.be/PgaQpxzT_0g>`_    | `Online Data Science Meetup @ ING WBAA <https://www.meetup.com/nl-NL/Tech-Meetups-ING/events/>`_ | July 8 2020      | Tomas Sostak            |
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+| `Popmon: Population Shift Monitoring Made Easy <https://www.youtube.com/watch?v=HE-3YeVYqPY>`_ | `PyData Fest Amsterdam 2020 <https://amsterdam.pydata.org/>`_                                    | June 16, 2020    | Tomas Sostak            |
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+| Popmon: Population Shift Monitoring Made Easy                                                  | `Amundsen Community Meetup <https://github.com/amundsen-io/amundsen>`_                           | June 4, 2020     | Max Baak                |
++------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------+------------------+-------------------------+
+
+
+Articles
+--------
+
++---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+------------------+----------------+
+| Title                                                                                                                                                                                             | Date             | Author         |
++---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+------------------+----------------+
+| `Popmon Open Source Package — Population Shift Monitoring Made Easy <https://medium.com/wbaa/population-monitoring-open-source-1ce3139d8c3a>`_                                                    | May 20, 2020     | Nicole Mpozika |
++---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+------------------+----------------+
+
+
 Project contributors
 ====================
 
@@ -171,3 +202,6 @@ Copyright ING WBAA. `popmon` is completely free, open-source and licensed under
 .. |notebook_incremental_data_colab| image:: https://colab.research.google.com/assets/colab-badge.svg
     :alt: Open in Colab
     :target: https://colab.research.google.com/github/ing-bank/popmon/blob/master/popmon/notebooks/popmon_tutorial_incremental_data.ipynb
+.. |downloads| image:: https://pepy.tech/badge/popmon
+    :alt: PyPi downloads
+    :target: https://pepy.tech/project/popmon
diff --git a/popmon/alerting/alerts_summary.py b/popmon/alerting/alerts_summary.py
@@ -44,7 +44,7 @@ def __init__(
 
         :param str read_key: key of input data to read from datastore.
         :param str store_key: key of output data to store in datastore (optional).
-        :param str combined_variable: name of artifical variable that combines all alerts. default is '_AGGREGATE_'.
+        :param str combined_variable: name of artificial variable that combines all alerts. default is '_AGGREGATE_'.
         :param list features: features of data frames to pick up from input data (optional).
         :param list ignore_features: list of features to ignore (optional).
         """
@@ -77,7 +77,7 @@ def transform(self, datastore):
             df = (self.get_datastore_object(data, feature, dtype=pd.DataFrame)).copy(
                 deep=False
             )
-            df.columns = [feature + "_" + c for c in df.columns]
+            df.columns = [f"{feature}_{c}" for c in df.columns]
             df_list.append(df)
 
         # the different features could technically have different indices.
@@ -99,8 +99,8 @@ def transform(self, datastore):
         dfc["worst"] = tlv[cols].values.max(axis=1) if len(cols) else 0
         # colors of traffic lights
         for color in ["green", "yellow", "red"]:
-            cols = fnmatch.filter(tlv.columns, "*_n_{}".format(color))
-            dfc["n_{}".format(color)] = tlv[cols].values.sum(axis=1) if len(cols) else 0
+            cols = fnmatch.filter(tlv.columns, f"*_n_{color}")
+            dfc[f"n_{color}"] = tlv[cols].values.sum(axis=1) if len(cols) else 0
 
         # store combination of traffic alerts
         data[self.combined_variable] = dfc

diff --git a/popmon/hist/histogram.py b/popmon/hist/histogram.py
@@ -211,7 +211,7 @@ def __repr__(self):
         return f"HistogramContainer(dtype={self.npdtype}, n_dims={self.n_dim})"
 
     def __str__(self):
-        return str(self)
+        return repr(self)
 
     def _edit_name(self, axis_name, xname, yname, convert_time_index, short_keys):
         if convert_time_index and self.is_ts:

diff --git a/popmon/notebooks/popmon_tutorial_advanced.ipynb b/popmon/notebooks/popmon_tutorial_advanced.ipynb
@@ -4,7 +4,6 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "collapsed": false,
     "jupyter": {
      "outputs_hidden": false
     },
@@ -26,10 +25,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%capture\n",
     "# install popmon (if not installed yet)\n",
     "import sys\n",
     "\n",
-    "!{sys.executable} -m pip install popmon"
+    "!\"{sys.executable}\" -m pip install popmon"
    ]
   },
   {
@@ -145,11 +145,13 @@
    "outputs": [],
    "source": [
     "# download histogrammar jar files if not already installed, used for histogramming of spark dataframe\n",
-    "from pyspark.sql import SparkSession\n",
+    "try:\n",
+    "    from pyspark.sql import SparkSession\n",
     "\n",
-    "spark = SparkSession.builder.config(\n",
-    "    \"spark.jars.packages\", \"org.diana-hep:histogrammar-sparksql_2.11:1.0.4\"\n",
-    ").getOrCreate()"
+    "    pyspark_installed = True\n",
+    "except ImportError:\n",
+    "    print(\"pyspark needs to be installed for this example\")\n",
+    "    pyspark_installed = False"
    ]
   },
   {
@@ -158,18 +160,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sdf = spark.createDataFrame(df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sdf.pm_stability_report(\n",
-    "    time_axis=\"DATE\", time_width=\"1w\", time_offset=\"2015-07-02\", extended_report=False\n",
-    ")"
+    "if pyspark_installed:\n",
+    "    spark = SparkSession.builder.config(\n",
+    "        \"spark.jars.packages\", \"org.diana-hep:histogrammar-sparksql_2.11:1.0.4\"\n",
+    "    ).getOrCreate()\n",
+    "\n",
+    "    sdf = spark.createDataFrame(df)\n",
+    "\n",
+    "    sdf.pm_stability_report(\n",
+    "        time_axis=\"DATE\",\n",
+    "        time_width=\"1w\",\n",
+    "        time_offset=\"2015-07-02\",\n",
+    "        extended_report=False,\n",
+    "    )"
    ]
   },
   {
@@ -287,7 +290,7 @@
    "outputs": [],
    "source": [
     "split_hist = split_hists.query(\"date == '2015-07-05 12:00:00'\")\n",
-    "split_hist.histogram[0].hist.plot.matplotlib();"
+    "split_hist.histogram[0].hist.plot.matplotlib()"
    ]
   },
   {
@@ -303,7 +306,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "split_hist.histogram_ref[0].hist.plot.matplotlib();"
+    "split_hist.histogram_ref[0].hist.plot.matplotlib()"
    ]
   },
   {
@@ -320,11 +323,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pickle\n",
+    "# As HTML report\n",
+    "report.to_file(\"report.html\")\n",
     "\n",
-    "with open(\"report.pkl\", \"wb\") as f:\n",
-    "    pickle.dump(report, f)\n",
-    "report.to_file(\"report.html\")"
+    "# Alternatively, as serialized Python object\n",
+    "# import pickle\n",
+    "\n",
+    "# with open(\"report.pkl\", \"wb\") as f:\n",
+    "#     pickle.dump(report, f)"
    ]
   },
   {
@@ -473,18 +479,18 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.7"
+   "version": "3.8.6"
   },
   "nteract": {
    "version": "0.15.0"
   },
   "pycharm": {
    "stem_cell": {
     "cell_type": "raw",
-    "source": [],
     "metadata": {
      "collapsed": false
-    }
+    },
+    "source": []
    }
   }
  },

diff --git a/popmon/notebooks/popmon_tutorial_basic.ipynb b/popmon/notebooks/popmon_tutorial_basic.ipynb
@@ -4,7 +4,6 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "collapsed": false,
     "jupyter": {
      "outputs_hidden": false
     },
@@ -36,10 +35,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%capture\n",
     "# install popmon (if not installed yet)\n",
     "import sys\n",
     "\n",
-    "!{sys.executable} -m pip install popmon"
+    "!\"{sys.executable}\" -m pip install popmon"
    ]
   },
   {

diff --git a/popmon/notebooks/popmon_tutorial_incremental_data.ipynb b/popmon/notebooks/popmon_tutorial_incremental_data.ipynb
@@ -28,10 +28,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "%%capture\n",
     "# install popmon (if not installed yet)\n",
     "import sys\n",
     "\n",
-    "!{sys.executable} -m pip install popmon"
+    "!\"{sys.executable}\" -m pip install popmon"
    ]
   },
   {

diff --git a/popmon/pipeline/report_pipelines.py b/popmon/pipeline/report_pipelines.py
@@ -18,7 +18,7 @@
 # CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 
-from pathlib import PosixPath
+from pathlib import Path
 
 from ..base import Pipeline
 from ..config import config
@@ -30,6 +30,7 @@
     metrics_self_reference,
 )
 from ..visualization import (
+    AlertSectionGenerator,
     HistogramSection,
     ReportGenerator,
     SectionGenerator,
@@ -46,7 +47,7 @@ def self_reference(
     features=None,
     skip_empty_plots=True,
     last_n=0,
-    plot_hist_n=2,
+    plot_hist_n=6,
     report_filepath=None,
     show_stats=None,
     **kwargs,
@@ -160,7 +161,7 @@ def rolling_reference(
     features=None,
     skip_empty_plots=True,
     last_n=0,
-    plot_hist_n=2,
+    plot_hist_n=6,
     report_filepath=None,
     show_stats=None,
     **kwargs,
@@ -218,7 +219,7 @@ def expanding_reference(
     features=None,
     skip_empty_plots=True,
     last_n=0,
-    plot_hist_n=2,
+    plot_hist_n=6,
     report_filepath=None,
     show_stats=None,
     **kwargs,
@@ -284,7 +285,7 @@ def __init__(
         last_n=0,
         skip_first_n=0,
         skip_last_n=0,
-        plot_hist_n=2,
+        plot_hist_n=6,
     ):
         """Initialize an instance of Report.
 
@@ -329,35 +330,35 @@ def sg_kws(read_key):
             #       - a section showing all traffic light alerts of monitored statistics
             #       - a section with a summary of traffic light alerts
             # --- o generate report
-            SectionGenerator(
-                dynamic_bounds="dynamic_bounds",
-                section_name=profiles_section,
-                static_bounds="static_bounds",
-                ignore_stat_endswith=["_mean", "_std", "_pull"],
-                **sg_kws("profiles"),
+            HistogramSection(
+                read_key="split_hists",
+                store_key=sections_key,
+                section_name=histograms_section,
+                hist_name_starts_with="histogram",
+                last_n=plot_hist_n,
+                description=descs.get("histograms", ""),
             ),
+            TrafficLightSectionGenerator(
+                section_name=traffic_lights_section, **sg_kws("traffic_lights")
+            ),
+            AlertSectionGenerator(section_name=alerts_section, **sg_kws("alerts")),
             SectionGenerator(
                 dynamic_bounds="dynamic_bounds_comparisons",
                 static_bounds="static_bounds_comparisons",
                 section_name=comparisons_section,
                 ignore_stat_endswith=["_mean", "_std", "_pull"],
                 **sg_kws("comparisons"),
             ),
-            TrafficLightSectionGenerator(
-                section_name=traffic_lights_section, **sg_kws("traffic_lights")
-            ),
-            SectionGenerator(section_name=alerts_section, **sg_kws("alerts")),
-            HistogramSection(
-                read_key="split_hists",
-                store_key=sections_key,
-                section_name=histograms_section,
-                hist_name_starts_with="histogram",
-                last_n=plot_hist_n,
-                description=descs.get("histograms", ""),
+            SectionGenerator(
+                dynamic_bounds="dynamic_bounds",
+                section_name=profiles_section,
+                static_bounds="static_bounds",
+                ignore_stat_endswith=["_mean", "_std", "_pull"],
+                **sg_kws("profiles"),
             ),
             ReportGenerator(read_key=sections_key, store_key=store_key),
         ]
-        if isinstance(report_filepath, (str, PosixPath)) and len(report_filepath) > 0:
+        if isinstance(report_filepath, (str, Path)) and len(report_filepath) > 0:
             self.modules.append(FileWriter(store_key, file_path=report_filepath))
 
     def transform(self, datastore):

diff --git a/popmon/version.py b/popmon/version.py
@@ -1,6 +1,6 @@
 """THIS FILE IS AUTO-GENERATED BY SETUP.PY."""
 
 name = "popmon"
-version = "0.3.10"
-full_version = "0.3.10"
+version = "0.3.11"
+full_version = "0.3.11"
 release = True
diff --git a/popmon/visualization/__init__.py b/popmon/visualization/__init__.py
@@ -20,14 +20,15 @@
 
 # flake8: noqa
 
+from popmon.visualization.alert_section_generator import AlertSectionGenerator
 from popmon.visualization.histogram_section import HistogramSection
 from popmon.visualization.report_generator import ReportGenerator
 from popmon.visualization.section_generator import SectionGenerator
 from popmon.visualization.traffic_light_section_generator import (
     TrafficLightSectionGenerator,
 )
 
-# set matplotlib backend to batchmode when running in shell
+# set matplotlib backend to batch mode when running in shell
 # need to do this *before* matplotlib.pyplot gets imported
 from ..visualization.backend import set_matplotlib_backend
 
@@ -39,4 +40,5 @@
     "HistogramSection",
     "ReportGenerator",
     "TrafficLightSectionGenerator",
+    "AlertSectionGenerator",
 ]