I have one input file in which there is one row where multiple mu(μ) characters are there. Python code just open the file and does some manipulation and we save that file in .csv format. When I save that file in .csv it is producing some weird and funny characters (�). The attached images show the input file and output files when I open in Excel.
Input CSV file:
Output CSV file:
from pathlib import Path
import pandas as pd
import time
import argparse
parser = argparse.ArgumentParser(description='Process some integers.')
parser.add_argument('path',
help='define the directory to folder/file')
start = time.time()
def main(path_files):
rs_columns = "SourceFile,RowNum,SampleID,Method,Element,Result".split(",")
rs = pd.DataFrame(columns=rs_columns)
if path_files.is_file():
fnames = [path_files]
else:
fnames = list(Path(path_files).glob("*.csv"))
for fn in fnames:
if "csv" in str(fn):
#df = pd.read_csv(str(fn))
df = pd.read_csv(str(fn), header=None, sep='\n')
df = df[0].str.split(',', expand=True)
else:
print("Unknown file", str(fn))
non_null_columns = [col for col in df.columns if df.loc[:, col].notna().any()]
# loop thru each column for the whole file and create a row of results in the output file
for i in range(1,len(non_null_columns)):
SourceFile = Path(fn.name)
Method = "WetScreening"
Element = df.iloc[1,i]
print(Element)
for j in range(2,len(df)):
RowNum = j+1
Result = df.iloc[j,i]
SampleID = df.iloc[j,0]
rs = rs.append(pd.DataFrame({
"SourceFile": [SourceFile],
"RowNum": [RowNum],
"SampleID": [SampleID],
"Method": [Method],
"Element": [Element],
"Result": [Result]
}),ignore_index=True)
rs.to_csv("check.csv",index=False)
print("Output: check.csv")
if __name__== "__main__":
start = time.time()
args = parser.parse_args()
path = Path(args.path)
main(path)
print("Processed time: ", time.time()-start)
Attach files here
Any help????
