import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from scipy import stats
# Doc: https://python-graph-gallery.com/seaborn/   https://seaborn.pydata.org/
comments = pd.read_csv("Ab_WSDM2018/comment.csv")
comments['msg_len'] = comments.apply(lambda x: len(str(x['msg'])),axis=1)
comments.head()
gid pid cid timeStamp id name rid msg msg_len
0 117291968282998 117291968282998_1219433751402142 1219543508057833 2016-06-03 20:06:42 1066539990059879 Julie Brissett NaN Michelle Bernstein - maybe try posting on the ... 89
1 117291968282998 117291968282998_1219433751402142 1219543508057833 2016-06-03 21:31:56 1066539990059879 Julie Brissett 1.021047e+16 Thank you! I didn{APOST}t know about that page. 48
2 117291968282998 117291968282998_1219433751402142 1219565831388934 2016-06-03 21:00:11 10210591844571055 Tracy Karfunkle Werner NaN Emma Werner 11
3 117291968282998 117291968282998_1219433751402142 1219610008051183 2016-06-03 22:41:32 1613040562360170 Susan Gimbel NaN Definitely interested! ! Please PMme{COMMA} I ... 118
4 117291968282998 117291968282998_1217805638231620 1217806108231573 2016-06-01 01:00:10 10104267024969633 Gabrielle Joella NaN I read a headline the other day that said it{A... 158
sns.distplot(comments['msg_len']);
/srv/paws/lib/python3.6/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.
  warnings.warn("The 'normed' kwarg is deprecated, and has been "