NLP in python to test sentiments in mailbox

config.py

import nltk
nltk.download('stopwords')

run.sh

echo "Installing dependencies"
brew install python
pip install ipython
pip install pandas
pip install nltk
echo "\n\nConfiguring ..."
ipython --quiet config.py
ipython sent_analysis.py

sent_analysis.py

from mailbox import mbox
import pandas as pd

def store_content(message, body=None):
    if not body:
        body = message.get_payload(decode=True)
    if len(message):
        contents = {
            "subject": message['subject'] or "",
            "body": body,
            "from": message['from'],
            "to": message['to'],
            "date": message['date'],
            "labels": message['X-Gmail-Labels'],
            "epilogue": message.epilogue,
        }
        return df.append(contents, ignore_index=True)

# Create an empty DataFrame with the relevant columns
df = pd.DataFrame(
    columns=("subject", "body", "from", "to", "date", "labels", "epilogue"))

# Import your downloaded mbox file
box = mbox('~/Desktop/Sent.mbox/mbox')

fails = []
for message in box:
    try:
        if message.get_content_type() == 'text/plain':
            df = store_content(message)
        elif message.is_multipart():
            # plaintext from multipart messages
            for part in message.get_payload():
                if part.get_content_type() == 'text/plain':
                    df = store_content(message, part.get_payload(decode=True))
                    break
    except:
        fails.append(message)

from nltk.corpus import stopwords

from collections import Counter

subject_word_bag = df.subject.apply(lambda t: t.lower() + " ").sum()

stops = [unicode(word) for word in stopwords.words('english')] + ['re:', 'fwd:', '-']
subject_words = [word for word in subject_word_bag.split() if word.lower() not in stops]

from textblob import TextBlob
df['feels'] = df.subject.apply(
    lambda s: TextBlob(unicode(s, errors='ignore')).sentiment.polarity)

sum = 0
for score in df['feels']:
    sum += score

print "Total mails - " + str(len(df['subject']) - 1)
print sum