my_NB.py

import pandas as pd
import numpy as np
from collections import Counter

class my_NB:

    def __init__(self, alpha=1):
        # alpha: smoothing factor
        # P(xi = t | y = c) = (N(t,c) + alpha) / (N(c) + n(i)*alpha)
        # where n(i) is the number of available categories (values) of feature i
        # Setting alpha = 1 is called Laplace smoothing
        self.alpha = alpha

    def fit(self, X, y):
        # X: pd.DataFrame, independent variables, str
        # y: list, np.array or pd.Series, dependent variables, int or str
        self.classes_ = list(set(list(y)))
        # Calculate P(yj) and P(xi|yj)        
        # make sure to use self.alpha in the __init__() function as the smoothing factor when calculating P(xi|yj)
        # write your code below
        return

    def predict(self, X):
        # X: pd.DataFrame, independent variables, str
        # return predictions: list
        # write your code below
        return predictions

    def predict_proba(self, X):
        # X: pd.DataFrame, independent variables, str
        # prob is a dict of prediction probabilities belonging to each categories
        # return probs = pd.DataFrame(list of prob, columns = self.classes_)                
        # P(yj|x) = P(x|yj)P(yj)/P(x)
        # write your code below
        return probs