apply some suggestions, including making plotting more efficient.

Author: ehinman

demos/WaterData_demo.ipynb

@@ -90,6 +90,19 @@
     "Let's get into some examples using the functions listed above. First, we need to load the `waterdata` module and a few other packages and functions to go through the examples. To run the entirety of this notebook, you will need to install `dataretrieval`, `matplotlib`, and `geopandas` packages. `matplotlib` is needed to create the plots, and `geopandas` is needed to create the interactive maps."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd626a14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install necessary packages to run notebook\n",
+    "!pip install dataretrieval\n",
+    "!pip install matplotlib\n",
+    "!pip install geopandas"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -105,14 +118,7 @@
     "from datetime import datetime, timedelta\n",
     "from datetime import date\n",
     "from dateutil.relativedelta import relativedelta\n",
-    "from dataretrieval import waterdata\n",
-    "\n",
-    "# Check if geopandas is installed\n",
-    "import importlib.util\n",
-    "if importlib.util.find_spec(\"geopandas\") is None:\n",
-    "    GEOPANDAS=False\n",
-    "else:\n",
-    "    GEOPANDAS=True"
+    "from dataretrieval import waterdata"
    ]
   },
   {
@@ -302,8 +308,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "if GEOPANDAS:\n",
-    "    NE_locations_discharge.set_crs(crs=\"WGS84\").explore()"
+    "NE_locations_discharge.set_crs(crs=\"WGS84\").explore()"
    ]
   },
   {
@@ -347,9 +352,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "if GEOPANDAS:\n",
-    "    latest_dv['date'] = latest_dv['time'].astype(str)\n",
-    "    latest_dv[['geometry', 'monitoring_location_id', 'date', 'value', 'unit_of_measure']].set_crs(crs=\"WGS84\").explore(column='value', tiles='CartoDB dark matter', cmap='YlOrRd', scheme=None, legend=True)"
+    "latest_dv['date'] = latest_dv['time'].astype(str)\n",
+    "latest_dv[['geometry', 'monitoring_location_id', 'date', 'value', 'unit_of_measure']].set_crs(crs=\"WGS84\").explore(column='value', tiles='CartoDB dark matter', cmap='YlOrRd', scheme=None, legend=True)"
    ]
   },
   {
@@ -373,10 +377,8 @@
     "    statistic_id=\"00011\"\n",
     ")\n",
     "\n",
-    "if GEOPANDAS:\n",
-    "    latest_instantaneous['datetime'] = latest_instantaneous['time'].astype(str)\n",
-    "\n",
-    "    latest_instantaneous[['geometry', 'monitoring_location_id', 'datetime', 'value', 'unit_of_measure']].set_crs(crs=\"WGS84\").explore(column='value', cmap='YlOrRd', scheme=None, legend=True)"
+    "latest_instantaneous['datetime'] = latest_instantaneous['time'].astype(str)\n",
+    "latest_instantaneous[['geometry', 'monitoring_location_id', 'datetime', 'value', 'unit_of_measure']].set_crs(crs=\"WGS84\").explore(column='value', cmap='YlOrRd', scheme=None, legend=True)"
    ]
   },
   {
@@ -413,7 +415,7 @@
    "id": "c5c5881e",
    "metadata": {},
    "source": [
-    "Currently, users may only request 3 years or less of continuous data in one pull. For this example, let's pull the last 1 year of daily mean values and instantaneous values for these Missouri River sites. We'll skip pulling geometry in the `waterdata.get_daily()` function; the `waterdata.get_continuous()` function does not return geometry at all."
+    "Currently, users may only request 3 years or less of continuous data in one pull. For this example, let's pull the last 1 year of daily mean values and instantaneous values for these Missouri River sites. We'll skip pulling geometry in the `waterdata.get_daily()` function; the `waterdata.get_continuous()` function does not return geometry at all to economize the size of the dataset returned."
    ]
   },
   {
@@ -459,6 +461,14 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "c1663311",
+   "metadata": {},
+   "source": [
+    "With these two datasets, let's plot daily and instantaneous discharge values for the four Missouri River sites using `matplotlib`. We will plot each site on a different subplot, with instantaneous values represented by a blue line and daily mean values represented by black points."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -540,65 +550,35 @@
    "id": "e621e45a",
    "metadata": {},
    "source": [
-    "Hey! We have some! Let's add these to our plots."
+    "Hey! We have some! Let's add these to our plots from above. We'll loop through each monitoring location plot and add in field measurements as red points."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "87a397a4",
+   "id": "42f22d69",
    "metadata": {},
    "outputs": [],
    "source": [
-    "fig, axes = plt.subplots(2, 2, figsize=(14, 8), dpi=150, sharex=False, sharey=True)\n",
-    "axes = axes.ravel()\n",
-    "\n",
-    "# Y-axis formatter (with thousands separators)\n",
-    "tick_fmt = mtick.StrMethodFormatter('{x:,.0f}')\n",
+    "for ax, site in zip(axes, missouri_site_ids):\n",
+    "    field = field_measurements.loc[\n",
+    "        field_measurements['monitoring_location_id'] == site, [\"time\", \"value\"]\n",
+    "    ].sort_values(\"time\")\n",
     "\n",
-    "for ax, site, site_name in zip(axes, missouri_site_ids, missouri_site_names):\n",
-    "    # Filter per site & sort by time\n",
-    "    inst = instantaneous_values.loc[instantaneous_values['monitoring_location_id'] == site, [\"time\", \"value\"]].sort_values(\"time\")\n",
-    "    daily = daily_values.loc[daily_values['monitoring_location_id'] == site, [\"time\", \"value\"]].sort_values(\"time\")\n",
-    "    field = field_measurements.loc[field_measurements['monitoring_location_id'] == site, [\"time\", \"value\"]].sort_values(\"time\")\n",
-    "\n",
-    "    # Instantaneous (line)\n",
-    "    ax.plot(\n",
-    "        inst[\"time\"], inst[\"value\"],\n",
-    "        color=\"#1f77b4\", lw=1.0, label=\"Instantaneous\", zorder=1\n",
-    "    )\n",
-    "\n",
-    "    # Daily mean (black dots)\n",
-    "    ax.scatter(\n",
-    "        daily[\"time\"], daily[\"value\"],\n",
-    "        c=\"black\", s=2, label=\"Daily mean\", zorder=2\n",
-    "    )\n",
-    "\n",
-    "    # Field measurements (red dots)\n",
     "    ax.scatter(\n",
     "        field[\"time\"], field[\"value\"],\n",
     "        c=\"red\", s=4, label=\"Field\", zorder=3\n",
     "    )\n",
     "\n",
-    "    # Axes styling\n",
-    "    ax.set_title(f\"{site}\\n{site_name}\", fontsize=10)\n",
-    "    ax.grid(True, which=\"both\", alpha=0.25)\n",
-    "    ax.yaxis.set_major_formatter(tick_fmt)\n",
-    "\n",
-    "    # Time ticks\n",
-    "    ax.xaxis.set_major_locator(mdates.MonthLocator())\n",
-    "    ax.xaxis.set_major_formatter(mdates.DateFormatter(\"%b %Y\"))\n",
-    "    ax.xaxis.set_minor_locator(mdates.WeekdayLocator(byweekday=mdates.MO))\n",
-    "\n",
-    "axes[0].set_ylabel(\"Discharge (cubic feet per second)\")\n",
-    "axes[2].set_ylabel(\"Discharge (cubic feet per second)\")\n",
-    "axes[2].set_xlabel(\"\")\n",
-    "axes[3].set_xlabel(\"\")\n",
-    "\n",
+    "# Remove any existing figure-level legends\n",
+    "for leg in fig.legends:\n",
+    "    leg.remove()\n",
     "handles, labels = axes[-1].get_legend_handles_labels()\n",
     "fig.legend(handles, labels, loc=\"lower center\", ncol=3, frameon=False)\n",
-    "fig.suptitle(f\"Missouri River sites - Daily Mean, Instantaneous, and Field Measurement Discharge\")\n",
-    "fig.autofmt_xdate()\n"
+    "\n",
+    "# Redraw the figure\n",
+    "fig.canvas.draw_idle()\n",
+    "fig\n"
    ]
   },
   {