lint

more lint

Author: aysim319

doctor_visits/delphi_doctor_visits/process_data.py

@@ -1,34 +1,40 @@
-import dask.dataframe as dd
+"""Module providing functions for processing and wrangling data."""
+
 from datetime import datetime
+from pathlib import Path
+
 import numpy as np
 import pandas as pd
-from pathlib import Path
 
+import dask.dataframe as dd
 from .config import Config
 
 def format_outname(prefix: str, se: bool, weekday:bool):
-    '''
+    """
+    Write out results.
 
     Parameters
     ----------
-    prefix
-    se
-    weekday
+    prefix:
+    se: boolean to write out standard errors, if true, use an obfuscated name
+    weekday: boolean for weekday adjustments.
+             signals will be generated with weekday adjustments (True) or without
+                adjustments (False)
 
     Returns
     -------
-
-    '''
-    # write out results
+    outname str
+    """
     out_name = "smoothed_adj_cli" if weekday else "smoothed_cli"
     if se:
         assert prefix is not None, "template has no obfuscated prefix"
         out_name = prefix + "_" + out_name
     return out_name
 
 def format_df(df: pd.DataFrame, geo_id: str, se: bool, logger):
-    '''
-    format dataframe and checks for anomalies to write results
+    """
+    Format dataframe and checks for anomalies to write results.
+
     Parameters
     ----------
     df: dataframe from output from update_sensor
@@ -39,7 +45,7 @@ def format_df(df: pd.DataFrame, geo_id: str, se: bool, logger):
     Returns
     -------
     filtered and formatted dataframe
-    '''
+    """
     # report in percentage
     df['val'] = df['val'] * 100
     df["se"] = df["se"] * 100
@@ -66,7 +72,7 @@ def format_df(df: pd.DataFrame, geo_id: str, se: bool, logger):
         valid_cond = (df['se'] > 0) & (df['val'] > 0)
         invalid_df = df[~valid_cond]
         if len(invalid_df) > 0:
-            logger.info(f"p=0, std_err=0 invalid")
+            logger.info("p=0, std_err=0 invalid")
         df = df[valid_cond]
     else:
         df["se"] = np.NAN
@@ -76,7 +82,8 @@ def format_df(df: pd.DataFrame, geo_id: str, se: bool, logger):
     return df
 
 def write_to_csv(output_df: pd.DataFrame, prefix: str, geo_id: str, weekday: bool, se:bool, logger, output_path="."):
-    """Write sensor values to csv.
+    """
+    Write sensor values to csv.
 
     Args:
       output_dict: dictionary containing sensor rates, se, unique dates, and unique geo_id
@@ -106,9 +113,9 @@ def write_to_csv(output_df: pd.DataFrame, prefix: str, geo_id: str, weekday: boo
 
 
 def csv_to_df(filepath: str, startdate: datetime, enddate: datetime, dropdate: datetime, logger) -> pd.DataFrame:
-    '''
-    Reads csv using Dask and filters out based on date range and currently unused column,
-    then converts back into pandas dataframe.
+    """
+    Read csv using Dask, filters unneeded data, then converts back into pandas dataframe.
+
     Parameters
     ----------
       filepath: path to the aggregated doctor-visits data
@@ -117,7 +124,7 @@ def csv_to_df(filepath: str, startdate: datetime, enddate: datetime, dropdate: d
       dropdate: data drop date (YYYY-mm-dd)
 
     -------
-    '''
+    """
     filepath = Path(filepath)
     logger.info(f"Processing {filepath}")
 

doctor_visits/delphi_doctor_visits/update_sensor.py

@@ -7,7 +7,6 @@
  - 2020-04-30: Aaron Rumack (add megacounty code)
  - 2020-05-06: Aaron and Maria (weekday effects/other adjustments)
 """
-
 # standard packages
 from datetime import timedelta, datetime
 from multiprocessing import Pool, cpu_count
@@ -41,7 +40,6 @@ def update_sensor(
       se: boolean to write out standard errors, if true, use an obfuscated name
       logger: the structured logger
     """
-
     drange = lambda s, e: np.array([s + timedelta(days=x) for x in range((e - s).days)])
     fit_dates = drange(Config.FIRST_DATA_DATE, dropdate)
     burnindate = startdate - Config.DAY_SHIFT