Classification & Vector Spaces - Probability and Bayes’ Rule

import pandas as pd
import string 
raw_tweets=[
  "I am happy because I am learning NLP",
  "I am sad, I am not learning NLP",
  "I am happy, not sad",
  "I am sad, not happy",
]
def clean(tweet:str):
  return  tweet.translate(str.maketrans('', '', string.punctuation)).lower()
tweets = [clean(tweet) for tweet in raw_tweets]
labels=['+','-','+','-']
df = pd.DataFrame({'tweets': tweets, 'labels': labels})
df

	tweets	labels
0	i am happy because i am learning nlp	+
1	i am sad i am not learning nlp	-
2	i am happy not sad	+
3	i am sad not happy	-

import numpy as np
from collections import Counter
p_freq,n_freq = Counter(), Counter()
#print( df[df.labels == '+']['tweets'].to_list())
[p_freq.update(tweet.split()) for tweet in df[df.labels == '+']['tweets'].to_list()]
[n_freq.update(tweet.split()) for tweet in df[df.labels == '-']['tweets'].to_list()]
print(p_freq)
print(n_freq)
vocab = list(set(p_freq.keys()).union(set(n_freq.keys())))
pos_freq = [p_freq[word] for word in vocab ]
neg_freq = [n_freq[word] for word in vocab ]
vocab_df=pd.DataFrame({'vocab':vocab,'pos_freq':pos_freq,'neg_freq':neg_freq})
vocab_df['p_pos']=vocab_df.pos_freq/vocab_df.pos_freq.sum()
vocab_df['p_neg']=vocab_df.neg_freq/vocab_df.neg_freq.sum()
vocab_df['p_pos_sm']=(vocab_df.pos_freq+1)/(vocab_df.pos_freq.sum()+vocab_df.shape[1])
vocab_df['p_neg_sm']=(vocab_df.neg_freq+1)/(vocab_df.neg_freq.sum()+vocab_df.shape[1])
vocab_df['ratio']= vocab_df.p_pos_sm/vocab_df.p_neg_sm
vocab_df['lambda']= np.log(vocab_df.p_pos_sm/vocab_df.p_neg_sm)
pd.set_option('display.float_format', '{:.2f}'.format)
vocab_df
print(vocab_df.shape)

[None, None]

[None, None]

Counter({'i': 3, 'am': 3, 'happy': 2, 'because': 1, 'learning': 1, 'nlp': 1, 'not': 1, 'sad': 1})
Counter({'i': 3, 'am': 3, 'sad': 2, 'not': 2, 'learning': 1, 'nlp': 1, 'happy': 1})
(8, 9)

	vocab	pos_freq	neg_freq	p_pos	p_neg	p_pos_sm	p_neg_sm	ratio	lambda
0	learning	1	1	0.08	0.08	0.11	0.11	1.06	0.05
1	nlp	1	1	0.08	0.08	0.11	0.11	1.06	0.05
2	am	3	3	0.23	0.23	0.22	0.21	1.06	0.05
3	happy	2	1	0.15	0.08	0.17	0.11	1.58	0.46
4	not	1	2	0.08	0.15	0.11	0.16	0.70	-0.35
5	because	1	0	0.08	0.00	0.11	0.05	2.11	0.75
6	i	3	3	0.23	0.23	0.22	0.21	1.06	0.05
7	sad	1	2	0.08	0.15	0.11	0.16	0.70	-0.35

from IPython.display import Markdown
from tabulate import tabulate
table = [["Sun",696000,1989100000],
         ["Earth",6371,5973.6],
         ["Moon",1737,73.5],
         ["Mars",3390,641.85]]
Markdown(tabulate(
  table, 
  headers=["Planet","R (km)", "mass (x 10^29 kg)"]
))

Table 1: Planets

Planet	R (km)	mass (x 10^29 kg)
Sun	696000	1.9891e+09
Earth	6371	5973.6
Moon	1737	73.5
Mars	3390	641.85