statanalysis.py

import re
import pandas as pd

def special_count(string):
    count = 0
    for char in string:
        if char.isalpha():
            continue
        elif char.isdigit():
            continue
        elif char.isspace():
            continue
        else:
            count += 1
    return count

def quote_count(string):
    count = 0
    for char in string:
        if char == '"':
            count += 1
    return count

def markup_count(string):
    count = len(re.findall('[<U+]......[>]',string))
    return count

def punct_count(string):
    count = 0
    for char in string:
      if char in ('!', "," ,"\'" ,";" ,"\"", ".", "-" ,"?"):
            count += 1
    return count

df = pd.read_csv('latest.csv',encoding='ISO-8859-1',usecols=['text'])
values = df.values

df["special_char_count"] = df["text"].apply(special_count)
df["quote_count"] = df["text"].apply(quote_count)
df["markup_count"] = df["text"].apply(markup_count)
df["punct_count"] = df["text"].apply(punct_count)