Task02：数据读取与数据分析（1天）

import pandas as pd
import matplotlib.pyplot as plt
train_df = pd.read_csv('./train_set.csv', sep='\t', nrows=100)
train_df.head()

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

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

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

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])

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])

count     100.000000
mean      872.320000
std       923.138191
min        64.000000
25%       359.500000
50%       598.000000
75%      1058.000000
max      7125.000000
Name: text_len, dtype: float64
2405
('3750', 3702)
('5034', 1)
('3750', 99)
('900', 99)
('648', 96)