use xarray to drop info before converting to df

doc/source/example_notebooks/QUEST_argo_data_access.ipynb

@@ -325,7 +325,7 @@
    "source": [
     "filename = 'processed_ATL03_20220419002753_04111506_006_02.h5'\n",
     "\n",
-    "reader = ipx.Read(source=path+filename)"
+    "reader = ipx.Read(data_source=path+filename)"
    ]
   },
   {
@@ -361,19 +361,31 @@
     "user_expressions": []
    },
    "source": [
-    "To make the data more easily plottable, let's convert the data into a Pandas DataFrame. Note that this method is memory-intensive for ATL03 data, so users are suggested to look at small spatial domains to prevent the notebook from crashing."
+    "To make the data more easily plottable, let's convert the data into a Pandas DataFrame. Note that this method is memory-intensive for ATL03 data, so users are suggested to look at small spatial domains to prevent the notebook from crashing. Here, since we only have data from one granule and ground track, we have sped up the conversion to a dataframe by first removing extra xarray dimensions we don't need for our plots. Several of the other steps completed below have analogous operations in xarray that would further reduce memory requirements and computation times."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bc086db7-f5a1-4ba7-ba90-5b19afaf6808",
-   "metadata": {
-    "tags": []
-   },
+   "id": "50d23a8e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "is2_pd =(ds.squeeze()\n",
+    "        .reset_coords()\n",
+    "        .drop_vars([\"source_file\",\"data_start_utc\",\"data_end_utc\",\"gran_idx\"])\n",
+    "        .to_dataframe()\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "01bb5a12",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "is2_pd = ds.to_dataframe()"
+    "is2_pd"
    ]
   },
   {
@@ -385,9 +397,9 @@
    },
    "outputs": [],
    "source": [
-    "# Rearrange the data to only include \"ocean\" photons\n",
-    "is2_pd = is2_pd.reset_index(level=[0,1,2])\n",
-    "is2_pd_ocean = is2_pd[is2_pd.index==1]\n",
+    "# Create a new dataframe with only \"ocean\" photons, as indicated by the \"ds_surf_type\" flag\n",
+    "is2_pd = is2_pd.reset_index(level=[0,1])\n",
+    "is2_pd_ocean = is2_pd[is2_pd.ds_surf_type==1].drop(columns=\"photon_idx\")\n",
     "is2_pd_ocean"
    ]
   },
@@ -446,7 +458,7 @@
    "outputs": [],
    "source": [
     "# Drop time variables that would cause errors in explore() function\n",
-    "is2_gdf = is2_gdf.drop(['data_start_utc','data_end_utc','delta_time','atlas_sdp_gps_epoch'], axis=1)"
+    "is2_gdf = is2_gdf.drop(['delta_time','atlas_sdp_gps_epoch'], axis=1)"
    ]
   },
   {