# Let's create functions to calculate gini and entropy scores

# Imports
from math import log

# calcpercent calculates the number of samples and percentages of each class
def calcpercent(node):
    nodesum = sum(node.values())
    percents = {c:v/nodesum for c,v in node.items()}
    return nodesum, percents

# giniscore calculates the score for a node using above formula
def giniscore(node):
    nodesum, percents = calcpercent(node)
    score = round(1 - sum([i**2 for i in percents.values()]), 3)
    print('Gini Score for node {} : {}'.format(node, score))
    return score
    
# entropy score calculates the score for a node using above formula
def entropyscore(node):
    nodesum, percents = calcpercent(node)
    score = round(sum([-i*log(i,2) for i in percents.values()]), 3)
    print('Entropy Score for node {} : {}'.format(node, score))
    return score

# infogain calculates the information gain given parent node, child nodes and criterion
def infogain(parent, children, criterion):
    score = {'gini': giniscore, 'entropy': entropyscore}
    metric = score[criterion]
    parentscore = metric(parent)
    parentsum = sum(parent.values())
    weighted_child_score = sum([metric(i)*sum(i.values())/parentsum  for i in children])
    gain = round((parentscore - weighted_child_score),2)
    print('Information gain: {}'.format(gain))
    return gain

# Parent node
parent_node = {'Red': 3, 'Blue':4, 'Green':5 }

# Let's say after the split nodes are 
node1 = {'Red':3, 'Blue':4}
node2 = {'Green':5}

gini_gain = infogain(parent_node, [node1, node2], 'gini')

entropy_gain = infogain(parent_node, [node1, node2], 'entropy')

# Performance wise there is not much difference between entropy and gini scores.

# Imports 
import numpy as np
import pandas as pd
import os
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.ensemble import RandomForestClassifier

# Load Dataset 
# Dataset can be found at: https://www.kaggle.com/uciml/sms-spam-collection-dataset

df = pd.read_csv('spam.csv', encoding = 'latin-1' )

# Keep only necessary columns
df = df[['v2', 'v1']]

# Rename columns
df.columns = ['SMS', 'Type']
df.head()

# Let's view top 5 rows of the loaded dataset
df.head()

# Let's process the text data 
# Instantiate count vectorizer
countvec = CountVectorizer(ngram_range=(1,4), stop_words='english',  strip_accents='unicode', max_features=1000)
cdf = countvec.fit_transform(df.SMS)

# Instantiate algos
dt_gini = DecisionTreeClassifier(criterion='gini')
dt_entropy = DecisionTreeClassifier(criterion='entropy')

# ests = {'Logistic Regression':lr,'Decision tree': dt,'Random forest': rf, 'Naive Bayes': mnb}
ests = {'Decision tree with gini index': dt_gini, 'Decision tree with entropy': dt_unbal}

for est in ests:
    print("{} score: {}%".format(est, round(cross_val_score(ests[est],X=cdf.toarray(), y=df.Type.values, cv=5).mean()*100, 3)))
    print("\n")