fix readme

Author: gsheni

README.md

@@ -3,12 +3,9 @@
 <p align="center">
     <i>This repository is part of <a href="https://sdv.dev">The Synthetic Data Vault Project</a>, a project from <a href="https://datacebo.com">DataCebo</a>.</i>
 </p>
-
 <div align="left">
-<br/>
 
 # PyMetrics
-
 The PyMetrics project allows you to extract download metrics for Python libraries published on [PyPI](https://pypi.org/) and [Anaconda](https://www.anaconda.com/).
 
 The DataCebo team uses these scripts to report download counts for the libraries in the [SDV ecosystem](https://sdv.dev/) and other libraries.

pymetrics/anaconda.py

@@ -23,15 +23,6 @@
 TIME_COLUMN = 'time'
 PKG_COLUMN = 'pkg_name'
 ANACONDA_BUCKET_PATH = 's3://anaconda-package-data/conda'
-ANACONDA_COLUMNS = [
-    TIME_COLUMN,
-    'data_source',
-    PKG_COLUMN,
-    'pkg_version',
-    'pkg_platform',
-    'pkg_python',
-    'counts',
-]
 
 
 def _read_anaconda_parquet(URL, pkg_names=None):
@@ -188,12 +179,9 @@ def collect_anaconda_downloads(
             pkg_names=projects,
         )
         if len(new_downloads) > 0:
-            if len(previous) == 0:
-                previous = new_downloads
-            else:
-                # Keep only the newest data (on a per day basis) for all packages
-                previous = previous[previous[TIME_COLUMN].dt.date != iteration_datetime.date()]
-                previous = pd.concat([previous, new_downloads], ignore_index=True)
+            # Keep only the newest data (on a per day basis) for all packages
+            previous = previous[previous[TIME_COLUMN].dt.date != iteration_datetime.date()]
+            previous = pd.concat([previous, new_downloads], ignore_index=True)
 
     previous = previous.sort_values(TIME_COLUMN)
     LOGGER.info('Obtained %s new downloads', all_downloads_count - len(previous))

pymetrics/output.py

@@ -25,9 +25,6 @@ def get_path(folder, filename):
 
     Aware of both local and Google Drive path formats.
     """
-    if not folder:
-        return None
-
     if folder.endswith('/'):
         folder = folder[:-1]
 
@@ -167,9 +164,6 @@ def load_csv(csv_path, read_csv_kwargs=None):
         pd.DataFrame:
             CSV contents.
     """
-    if not csv_path:
-        return None
-
     if not csv_path.endswith('.csv'):
         csv_path += '.csv'