update abacus_plot to work with any format of detection file

Author: Brian Jones

py_notebooks/abacus_plot.ipynb

@@ -4,27 +4,23 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Abacus Plot\n",
+    "# 📈 Abacus Plot\n",
     "\n",
-    "The abacus plot is a way to plot annimal along time. The function uses Plotly to place your points on a scatter plot. ``ycolumn`` is used as the y axis and ``datecollected`` is used as the x axis. ``color_column`` is used to group detections together and assign them a color.\n",
-    "\n",
-    "<span style=\"color:red\">Warning:</span> \n",
-    "\n",
-    "    Input files must include ``datecollected`` as a column."
+    "The abacus plot is a way to plot annimal along time. The function uses Plotly to place your points on a scatter plot. ``ycolumn`` is used as the y axis and ``datecollected`` is used as the x axis. ``color_column`` is used to group detections together and assign them a color."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from resonate.abacus_plot import abacus_plot\n",
     "import pandas as pd\n",
     "\n",
-    "df = pd.read_csv('/path/to/detections.csv')"
+    "df = pd.read_csv('/path/to/detections.csv') # read csv\n",
+    "# or\n",
+    "# df = pd.read_parquet('/path/to/detections.parquet') # parquet file"
    ]
   },
   {
@@ -40,7 +36,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "abacus_plot(df, ycolumn='catalognumber', color_column='receiver_group')"
+    "abacus_plot(df, date_column='dateCollectedUTC',ycolumn='catalogNumber', color_column='station', uniqueid_column='unqDetecID')"
    ]
   },
   {
@@ -58,20 +54,11 @@
    "source": [
     "abacus_plot(df, ipython_display=False, filename='example.html')"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [default]",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -84,8 +71,8 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "python",
-   "version": "3.6.3"
+   "pygments_lexer": "ipython3",
+   "version": "3.9.21"
   },
   "varInspector": {
    "cols": {

resonate/abacus_plot.py

@@ -4,7 +4,8 @@
 from resonate.library.exceptions import GenericException
 
 
-def abacus_plot(detections: pd.DataFrame, ycolumn:str='catalognumber', color_column:str=None, ipython_display=True, title:str='Abacus Plot', filename:str=None):
+def abacus_plot(detections: pd.DataFrame, date_column='datecollected', uniqueid_column='unqdetecid',
+                ycolumn:str='catalognumber', color_column:str=None, ipython_display=True, title:str='Abacus Plot', filename:str=None):
     """Creates a plotly abacus plot from a pandas dataframe
 
     Args:
@@ -31,14 +32,14 @@ def abacus_plot(detections: pd.DataFrame, ycolumn:str='catalognumber', color_col
     if not isinstance(detections, pd.DataFrame):
         raise GenericException('input parameter must be a Pandas dataframe')
 
-    mandatory_columns = set(['datecollected', ycolumn])
+    mandatory_columns = set([date_column, ycolumn])
 
     if color_column is not None:
         mandatory_columns.add(color_column)
 
     if mandatory_columns.issubset(detections.columns):
 
-        detections = detections[~detections.unqdetecid.str.contains(
+        detections = detections[~detections[uniqueid_column].str.contains(
             'release')].reset_index(drop=True)
 
         if color_column is not None:
@@ -47,7 +48,7 @@ def abacus_plot(detections: pd.DataFrame, ycolumn:str='catalognumber', color_col
             for group in detections.groupby(color_column):
                 data.append(
                     {
-                        'x': group[1].datecollected.tolist(),
+                        'x': group[1][date_column].tolist(),
                         'y': group[1][ycolumn].tolist(),
                         'mode': 'markers',
                         'name': group[0]
@@ -56,7 +57,7 @@ def abacus_plot(detections: pd.DataFrame, ycolumn:str='catalognumber', color_col
         else:
             data = [
                 {
-                    'x': detections.datecollected.tolist(),
+                    'x': detections[date_column].tolist(),
                     'y': detections[ycolumn].tolist(),
                     'mode': 'markers',
                 }
@@ -66,8 +67,8 @@ def abacus_plot(detections: pd.DataFrame, ycolumn:str='catalognumber', color_col
             title=title,
             xaxis=dict(
                 autorange=False,
-                range=[detections.datecollected.min(
-                ), detections.datecollected.max()]
+                range=[detections[date_column].min(
+                ), detections[date_column].max()]
             ),
             yaxis=dict(
                 autorange=True