From 41e8ed94e85d96cd5ca2de723cc77538d2bba524 Mon Sep 17 00:00:00 2001
From: Davide Gamba <davide.gamba@cern.ch>
Date: Mon, 7 Jun 2021 13:18:28 +0200
Subject: [PATCH] style
---
datascout/_datascout.py | 38 +++++++++++++++++++++++---------------
1 file changed, 23 insertions(+), 15 deletions(-)
diff --git a/datascout/_datascout.py b/datascout/_datascout.py
index 4df2be1..cbcadec 100644
--- a/datascout/_datascout.py
+++ b/datascout/_datascout.py
@@ -15,9 +15,10 @@ import scipy
from pathlib import Path
+"""
######
# Functions needed to split 2D arrays
-
+"""
def _split_2D_array(val, in_memory=False, split_to_list=False, verbose=False):
"""It converts numpy 2D arrays into either 1D arrays or list of 1D arrays
@@ -71,7 +72,7 @@ def _convert_dict_list(data, in_memory=False, split_to_list=False, verbose=False
It is up to the user to make a deepcopy, if desired, of the data before and/or after conversion.
"""
- if in_memory == False:
+ if in_memory is False:
data = copy.copy(data)
if type(data) == list:
for i in range(len(data)):
@@ -98,9 +99,10 @@ def _convert_dict_list(data, in_memory=False, split_to_list=False, verbose=False
return data
+"""
######
# Functions needed to re-merge 1D arrays of 1D arrays into 2D arrays
-
+"""
def _merge_to_2D(val, string_as_obj=False, verbose=False):
"""
@@ -147,7 +149,7 @@ def _revert_dict_list(data, in_memory=False, string_as_obj=False, verbose=False)
"""
- if in_memory == False:
+ if in_memory is False:
data = copy.copy(data)
if type(data) == list:
for entry in data:
@@ -174,9 +176,11 @@ def _revert_dict_list(data, in_memory=False, string_as_obj=False, verbose=False)
return data
-######
+"""
+#
# CORE function of this project: it allows to convert a pyarrow object into a dict
#
+"""
def _convert_parrow_data(
data, treat_str_arrays_as_str=True, use_list_for_2D_array=False
):
@@ -191,7 +195,8 @@ def _convert_parrow_data(
if use_list_for_2D_array (default=False) it will try to use lists of 1D arrays instead of 2D arrays
Typically the output should be a `dict`. If, however, one is trying to convert more complex structures
- like a pyarrow Table or StructArray, the output will be a list of dictionaries, if more than one data records are found.
+ like a pyarrow Table or StructArray, the output will be a list of dictionaries if more than one data
+ records are found.
"""
if isinstance(data, pa.lib.Table):
output = []
@@ -276,8 +281,10 @@ def _convert_parrow_data(
return data
-###### Some important functions not so interesting for the standard user, but fundamental
-
+"""
+######
+# Some important functions not so interesting for the standard user, but fundamental
+"""
def dict_to_pyarrow(input_dict):
my_data_dict_converted = _convert_dict_list(
@@ -303,9 +310,9 @@ def pyarrow_to_dict(input_pa):
def pyarrow_to_pandas(input_pa):
return dict_to_pandas(pyarrow_to_dict(input_pa))
-
-####### The functions interesting for the user
-
+"""
+####### The functions interesting for the user are the following ones:
+"""
def dict_to_pandas(input_dict):
if not isinstance(input_dict, list):
@@ -399,11 +406,12 @@ def parquet_to_pandas(filename):
def parquet_to_awkward(filename):
return ak.from_parquet(filename)
-
+"""
####### Simple save/load functions for the user
+"""
def save_dict(dictData, folderPath=None, filename=None, fileFormat="parquet"):
- if filename == None:
+ if filename is None:
filename = datetime.now().strftime("%Y.%m.%d.%H.%M.%S.%f")
Path(folderPath).mkdir(parents=True, exist_ok=True)
filename = os.path.join(folderPath, filename)
@@ -434,9 +442,9 @@ def load_dict(filename, fileFormat="parquet"):
else:
raise ValueError("Unknown file format ({})".format(fileFormat))
-
+"""
####### Some additional functions for debugging purposes
-
+"""
def _find_lists(data, verbose=False):
"""
--
GitLab