Visualization

Author: rzats

docs/getting_started_with_epidatpy.rst

@@ -77,7 +77,7 @@ The ``pub_covidcast`` function lets us access the ``covidcast`` endpoint:
 
    print(apicall)
 
-``pub_covidcast`` returns an ``EpiDataCall``, which can be further converted into different output formats - such as a Pandas DataFrame:
+``pub_covidcast`` returns an ``EpiDataCall``, which is a not-yet-executed query that can be inspected. The query can be executed and converted to a DataFrame by using the ``.df()`` method:
 
 .. exec::
    :context: true
@@ -175,9 +175,29 @@ it using any of the available Python libraries:
 
 .. code-block:: python
    
-   data.plot(x="time_value", y="value", title="Smoothed CLI from Facebook Survey", xlabel="Date", ylabel="CLI")
-
-.. image:: images/Figure_1.png
+   import matplotlib.pyplot as plt
+
+   fig, ax = plt.subplots(figsize=(6, 5))
+   plt.rc("axes", titlesize=16)
+   plt.rc("axes", labelsize=16)
+   plt.rc("xtick", labelsize=14)
+   plt.rc("ytick", labelsize=14)
+   ax.spines["right"].set_visible(False)
+   ax.spines["left"].set_visible(False)
+   ax.spines["top"].set_visible(False)
+
+   data.pivot_table(values = "value", index = "time_value", columns = "geo_value").plot(
+      title="Smoothed CLI from Facebook Survey",
+      xlabel="Date",
+      ylabel="CLI",
+      ax = ax,
+      linewidth = 1.5
+   )
+
+   plt.subplots_adjust(bottom=.2)
+   plt.show()
+
+.. image:: images/Getting_Started.png
    :width: 800
    :alt: Smoothed CLI from Facebook Survey
 

docs/images/Figure_1.png

@@ -28,16 +28,20 @@ data streams which are publically accessible from the COVIDcast API. See the `da
 and signals documentation <https://cmu-delphi.github.io/delphi-epidata/api/covidcast_signals.html>`_
 for descriptions of the available sources.
 
->>> from epidatpy import CovidcastEpidata
->>> epidata = CovidcastEpidata()
->>> sources = epidata.source_df
->>> sources.head()
-            source                                         name                                        description          reference_signal                                            license                                                dua                                            signals
-0             chng                            Change Healthcare  Change Healthcare is a healthcare technology c...   smoothed_outpatient_cli                                           CC BY-NC  https://cmu.box.com/s/cto4to822zecr3oyq1kkk9xm...  smoothed_outpatient_cli,smoothed_adj_outpatien...
-1    covid-act-now                          Covid Act Now (CAN)  COVID Act Now (CAN) tracks COVID-19 testing st...  pcr_specimen_total_tests                                           CC BY-NC                                               None  pcr_specimen_positivity_rate,pcr_specimen_tota...
-2    doctor-visits                    Doctor Visits From Claims  Information about outpatient visits, provided ...              smoothed_cli                                              CC BY  https://cmu.box.com/s/l2tz6kmiws6jyty2azwb43po...                      smoothed_cli,smoothed_adj_cli
-3        fb-survey  Delphi US COVID-19 Trends and Impact Survey  We conduct the Delphi US COVID-19 Trends and I...              smoothed_cli                                              CC BY  https://cmu.box.com/s/qfxplcdrcn9retfzx4zniyug...  raw_wcli,raw_cli,smoothed_cli,smoothed_wcli,ra...
-4  google-symptoms                Google Symptoms Search Trends  Google's [COVID-19 Search Trends symptoms data...       s05_smoothed_search  To download or use the data, you must agree to...                                               None  ageusia_raw_search,ageusia_smoothed_search,ano...
+.. exec::
+  :context: true
+
+  from epidatpy import CovidcastEpidata
+  import pandas as pd
+
+  pd.set_option('display.max_columns', None)
+  pd.set_option('display.max_rows', None)
+  pd.set_option('display.width', 1000)
+
+  epidata = CovidcastEpidata()
+  sources = epidata.source_df
+
+  print(sources.head())
 
 This DataFrame contains the following columns:
 
@@ -52,14 +56,12 @@ The ``signal_df`` DataFrame can also be used to obtain information about the sig
 that are available - for example, what time range they are available for,
 and when they have been updated.
 
->>> signals = epidata.signal_df
->>> signals.head()
-  source                         signal                                          name  active                                  short_description                                        description time_type time_label value_label format category high_values_are  is_smoothed is_weighted is_cumulative has_stderr has_sample_size                        geo_types
-0   chng        smoothed_outpatient_cli                   COVID-Related Doctor Visits   False  Estimated percentage of outpatient doctor visi...  Estimated percentage of outpatient doctor visi...       day       Date       Value    raw    early             bad         True       False         False      False           False  county,hhs,hrr,msa,nation,state
-1   chng    smoothed_adj_outpatient_cli    COVID-Related Doctor Visits (Day-adjusted)   False  Estimated percentage of outpatient doctor visi...  Estimated percentage of outpatient doctor visi...       day       Date       Value    raw    early             bad         True       False         False      False           False  county,hhs,hrr,msa,nation,state
-2   chng      smoothed_outpatient_covid                 COVID-Confirmed Doctor Visits   False                      COVID-Confirmed Doctor Visits  Estimated percentage of outpatient doctor visi...       day       Date       Value    raw    early             bad         True       False         False      False           False  county,hhs,hrr,msa,nation,state
-3   chng  smoothed_adj_outpatient_covid  COVID-Confirmed Doctor Visits (Day-adjusted)   False                      COVID-Confirmed Doctor Visits  Estimated percentage of outpatient doctor visi...       day       Date       Value    raw    early             bad         True       False         False      False           False  county,hhs,hrr,msa,nation,state
-4   chng        smoothed_outpatient_flu             Influenza-Confirmed Doctor Visits   False  Estimated percentage of outpatient doctor visi...  Estimated percentage of outpatient doctor visi...       day        Day       Value    raw    early             bad         True       False         False       None            None  county,hhs,hrr,msa,nation,state
+.. exec::
+  :context: true
+
+  signals = epidata.signal_df
+
+  print(signals.head())
 
 This DataFrame contains one row each available signal, with the following columns:
 

docs/images/Getting_Started.png

@@ -90,6 +90,51 @@ for forecasting tasks. To backtest a forecasting model on past data, it is
 important to use the data that would have been available *at the time* the model
 was or would have been fit, not data that arrived much later.
 
+By plotting API results with different values of the ``as_of`` parameter, we can
+see how the indicator value changes over time as new observations become available:
+
+.. code-block:: python
+
+   results = []
+   for as_of_date in ["2020-05-07", "2020-05-14", "2020-05-21", "2020-05-28"]:
+      apicall = epidata.pub_covidcast(
+         data_source = "doctor-visits",
+         signals = "smoothed_adj_cli",
+         time_type = "day",
+         time_values = EpiRange("2020-04-20", "2020-04-27"),
+         geo_type = "state",
+         geo_values = "pa",
+         as_of = as_of_date)
+
+      results.append(apicall.df())
+
+   final_df = pd.concat(results)
+   final_df["issue"] = final_df["issue"].dt.date
+
+   fig, ax = plt.subplots(figsize=(6, 5))
+   ax.spines["right"].set_visible(False)
+   ax.spines["left"].set_visible(False)
+   ax.spines["top"].set_visible(False)
+
+   def sub_cmap(cmap, vmin, vmax):
+      return lambda v: cmap(vmin + (vmax - vmin) * v)
+
+   final_df.pivot_table(values = "value", index = "time_value", columns = "issue").plot(
+      xlabel="Date",
+      ylabel="CLI",
+      ax = ax,
+      linewidth = 1.5,
+      colormap=sub_cmap(plt.get_cmap('viridis').reversed(), 0.2, 1)
+   )
+
+   plt.title("Smoothed CLI from Doctor Visits", fontsize=16)
+   plt.subplots_adjust(bottom=.2)
+   plt.show()
+
+.. image:: images/Versioned_Data.png
+   :width: 800
+   :alt: Smoothed CLI from Facebook Survey
+
 Multiple issues of observations
 -------------------------------
 

docs/images/Versioned_Data.png

@@ -15,14 +15,62 @@
 apicall = epidata.pub_covidcast(
     data_source = "fb-survey",
     signals = "smoothed_cli", 
-    geo_type = "nation",
+    geo_type = "state",
+    geo_values = "pa,ca,fl",
     time_type = "day",
-    geo_values = "us",
     time_values = EpiRange(20210405, 20210410))
 print(apicall)
 
 data = apicall.df()
 
-data.plot(x="time_value", y="value", title="Smoothed CLI from Facebook Survey", xlabel="Date", ylabel="CLI")
+fig, ax = plt.subplots(figsize=(6, 5))
+ax.spines["right"].set_visible(False)
+ax.spines["left"].set_visible(False)
+ax.spines["top"].set_visible(False)
+
+data.pivot_table(values = "value", index = "time_value", columns = "geo_value").plot(
+    xlabel="Date",
+    ylabel="CLI",
+    ax = ax,
+    linewidth = 1.5
+)
+
+plt.title("Smoothed CLI from Facebook Survey", fontsize=16)
+plt.subplots_adjust(bottom=.2)
+plt.savefig("docs/images/Getting_Started.png", dpi=300)
+
+results = []
+for as_of_date in ["2020-05-07", "2020-05-14", "2020-05-21", "2020-05-28"]:
+    apicall = epidata.pub_covidcast(
+        data_source = "doctor-visits",
+        signals = "smoothed_adj_cli",
+        time_type = "day",
+        time_values = EpiRange("2020-04-20", "2020-04-27"),
+        geo_type = "state",
+        geo_values = "pa",
+        as_of = as_of_date)
+
+    results.append(apicall.df())
+
+final_df = pd.concat(results)
+final_df["issue"] = final_df["issue"].dt.date
+
+fig, ax = plt.subplots(figsize=(6, 5))
+ax.spines["right"].set_visible(False)
+ax.spines["left"].set_visible(False)
+ax.spines["top"].set_visible(False)
+
+def sub_cmap(cmap, vmin, vmax):
+    return lambda v: cmap(vmin + (vmax - vmin) * v)
+
+final_df.pivot_table(values = "value", index = "time_value", columns = "issue").plot(
+    xlabel="Date",
+    ylabel="CLI",
+    ax = ax,
+    linewidth = 1.5,
+    colormap=sub_cmap(plt.get_cmap('viridis').reversed(), 0.2, 1)
+)
+
+plt.title("Smoothed CLI from Doctor Visits", fontsize=16)
 plt.subplots_adjust(bottom=.2)
-plt.show()
+plt.savefig("docs/images/Versioned_Data.png", dpi=300)