Is their any function that i can use to read my csv file without any codec error?
import refrom nltk.stem import WordNetLemmatizerimport contractionsimport csvbasicdict = dict()temp_of_colums = []def preprocess_data(test): return testdef load_data(): sc_posrev = open("literally nothing\IMDBfileted.csv", mode="w", newline="") prev = csv.DictWriter(sc_posrev, fieldnames=["review", "sentiment"]) cs_file = open("literally nothing\IMDB Dataset.csv", mode="r", encoding="cp1252") csvfile = csv.DictReader(cs_file, delimiter=",") line = 0 for row in csvfile: # print(row) kilo = preprocess_data(row["review"]) print(line) if(line == 0): prev.writeheader() # print(row["review"]) line += 1 p = row["sentiment"].lower() if(p == "positive"): posrevl = [] prev.writerow({"review": kilo, "sentiment": 1}) elif(p == "negative"): prev.writerow({"review": kilo, "sentiment": 0}) if(line == 4000): break cs_file.close() sc_posrev.close()load_data()Error:
Traceback (most recent call last): File "d:\nothing\literally nothing\stackov.py", line 100, in <module> load_data() File "d:\nothing\literally nothing\stackov.py", line 80, in load_data for row in csvfile: File "C:\Users\Varun\AppData\Local\Programs\Python\Python310\lib\csv.py", line 111, in __next__ row = next(self.reader) File "C:\Users\Varun\AppData\Local\Programs\Python\Python310\lib\encodings\cp1252.py", line 23, in decode return codecs.charmap_decode(input,self.errors,decoding_table)[0]UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 6237: character maps to <undefined>line 211 refers to my function call and line 80 refers to iteratoriterating through the row in file it gives error and changing encodings gives me different types of errors