date extraction.py

    # import medical notes -->
    doc = []
    with open('dates.txt') as file:
        for line in file:
            doc.append(line)
    
    # create dataframe -->
    df = pd.DataFrame(doc, columns=['text'])
    
    # strip at \n --> 
    df['text'] = df['text'].apply(lambda x: x.strip('\n'))

    # capturing all date variants -->    
    pattern_dates = r'\d{1,2}\/\d{1,2}\/\d{2,4}|\d{1,2}\-\d{1,2}\-\d{2,4}|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]*\-\d{1,2}\-\d{4}|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]*[,.]? \d{2}[a-z]*,? \d{4}|\d{1,2} (?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z,.]* \d{4}|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]{2}[,.]* \d{4}|'+"[,.]? \d{4}|".join(month_name[1:])+"[,.]? \d{4}"+r'|\d{1,2}\/\d{4}|\d{4}'    
    df['date'] = df['text'].apply(lambda x:re.findall(pattern_dates,x))
    
    # fixing outlier 271 -->
    df['date'][271] = [df['date'][271][1]]
    
    #extract dates from dataframe -->
    df['date'] = df['date'].apply(lambda x: x[0])
    date_list = list(df['date'])