From b571e818c5eff1bd55a4f0043fe05176b3f8653c Mon Sep 17 00:00:00 2001
From: Hugo Gillet <hugo.gillet@stud.unibas.ch>
Date: Tue, 13 Dec 2022 09:34:29 +0000
Subject: [PATCH] Add new file
---
.../test_Functions.py | 132 ++++++++++++++++++
1 file changed, 132 insertions(+)
create mode 100644 test/Test_representative_and_match/test_Functions.py
diff --git a/test/Test_representative_and_match/test_Functions.py b/test/Test_representative_and_match/test_Functions.py
new file mode 100644
index 0000000..72a120d
--- /dev/null
+++ b/test/Test_representative_and_match/test_Functions.py
@@ -0,0 +1,132 @@
+import pandas as pd
+import numpy as np
+import os
+
+def find_path(filename:str)->str:
+ """Find the path to a file
+
+ Args:
+ name of a file
+
+ Returns:
+ str path of a file
+
+ Raises:
+ None
+ """
+ absolute_path = os.path.dirname(__file__)
+ test_file = "inputs\\" + str(filename)
+ full_path = os.path.join(absolute_path, test_file)
+ return full_path
+
+def find_output():
+ """Find the path of the output file
+
+ Args:
+ name of a file
+
+ Returns:
+ str path of a file
+
+ Raises:
+ None
+ """
+ absolute_path = os.path.dirname(__file__)
+ test_file = "ReprTrans_ExpressionLevel.tsv"
+ full_path = os.path.join(absolute_path, test_file)
+ return full_path
+
+
+def find_path_intermediateFile()->str:
+ """Find the path to gencode.vM31.annotation_intermediat_file.txt
+
+ Args:
+ none
+
+ Returns:
+ str path of gencode.vM31.annotation_intermediat_file.txt
+
+ Raises:
+ None
+ """
+ absolute_path = os.path.dirname(__file__)
+ test_file = r"inputs\test_gencode.vM31.annotation_intermediat_file.txt"
+ full_path = os.path.join(absolute_path, test_file)
+ return full_path
+
+def column_number(df :pd.DataFrame)-> int:
+
+ """Return the number of column of a df
+
+ Args:
+ dataframe
+
+ Returns:
+ int
+
+ Raises:
+ None
+ """
+ length = len(df.columns)
+ return length
+
+def column_dType(df : pd.DataFrame) -> dict[str,np.dtype]:
+ """Return the type of each column of a df in a dict
+
+ Args:
+ Pandas dataframe
+
+ Returns:
+ dict{column:np.dtype()}
+
+ Raises:
+ None
+ """
+ dtype=df.dtypes.to_dict()
+ return dtype
+
+def duplicated_rows(df: pd.DataFrame) -> pd.DataFrame:
+ """Return the sum of duplicated rows in a df
+
+ Args:
+ Pandas dataframe
+
+ Returns:
+ int
+
+ Raises:
+ None
+ """
+ df_dupl = df[df.duplicated()]
+ return df_dupl
+
+def duplicated_index(df: pd.DataFrame) -> pd.DataFrame:
+ """Return the sum of duplicated index in a df
+
+ Args:
+ Pandas dataframe
+
+ Returns:
+ int
+
+ Raises:
+ None
+ """
+ df_dupl = df[df.index.duplicated()]
+ return df_dupl
+
+def NA_value(df: pd.DataFrame) -> int:
+ """Return the sum of NA values in a df
+
+ Args:
+ Pandas dataframe
+
+ Returns:
+ int
+
+ Raises:
+ None
+ """
+ nNA = df.isna().sum().sum()
+ return nNA
+
--
GitLab