import pandas as pd
train_df = pd.read_csv('/home/xinjing/桌面/mydemo/DataWhale/15/NLP/datasets/train_set.csv',sep='\t')

train_df.head()

label text
0 2 2967 6758 339 2021 1854 3731 4109 3792 4149 15...
1 11 4464 486 6352 5619 2465 4802 1452 3137 5778 54...
2 3 7346 4068 5074 3747 5681 6093 1777 2226 7354 6...
3 2 7159 948 4866 2109 5520 2490 211 3956 5520 549...
4 3 3646 3055 3055 2490 4659 6065 3370 5814 2465 5...

%pylab inline
train_df['text_len'] = train_df['text'].apply(lambda x: len(x.split(' ')))
print(train_df['text_len'].describe())

Populating the interactive namespace from numpy and matplotlib
count 200000.000000
mean 907.207110
std 996.029036
min 2.000000
25% 374.000000
50% 676.000000
75% 1131.000000
max 57921.000000
Name: text_len, dtype: float64

_ = plt.hist(train_df['text_len'], bins=200)
plt.xlabel('Text char count')
plt.title("Histogram of char count")

Text(0.5, 1.0, 'Histogram of char count')

image.png

train_df['label'].value_counts().plot(kind='bar')
plt.title('News class count')
plt.xlabel("category")

Text(0.5, 0, 'category')

image.png

from collections import Counter
all_lines = ' '.join(list(train_df['text']))
word_count = Counter(all_lines.split(" "))
word_count = sorted(word_count.items(), key=lambda d:d[1], reverse = True)

print(len(word_count))

print(word_count[0])

print(word_count[-1])

6869
('3750', 7482224)
('3133', 1)

from collections import Counter
train_df['text_unique'] = train_df['text'].apply(lambda x: ' '.join(list(set(x.split(' ')))))
all_lines = ' '.join(list(train_df['text_unique']))
word_count = Counter(all_lines.split(" "))
word_count = sorted(word_count.items(), key=lambda d:int(d[1]), reverse = True)

print(word_count[0])

print(word_count[1])

print(word_count[2])

('3750', 197997)
('900', 197653)
('648', 191975)