///////////////////////////////////program 2////////////////////////////////////////
import pandas as pd
import numpy as np
data=pd.read_csv('pro2.csv')
data
features=np.array(data)[:,:-1]
features
target=np.array(data)[:,-1]
target
for i,h in enumerate(features):
    if target[i]=='yes':
        specific_h=features[i].copy()
    break
print("initializatio of specific_h and general_h")
print(specific_h)
general_h=[["?" for i in range(len(specific_h))]for i in range(len(specific_h))]
print(general_h)
for i,h in enumerate(features):
    if target[i]=="yes":
        for x in range(len(specific_h)):
            if h[x]!=specific_h[x]:
                specific_h[x]='?'
                general_h[x][x]='?'
    if target[i]=="no":
        for x in range(len(specific_h)):
            if h[x]!=specific_h[x]:
                general_h[x][x]=specific_h[x]
            else:
                general_h[x][x]='?'
print(specific_h,"\n")
print(general_h,"\n")
indices=[i for i,val in enumerate(general_h)if val==['?','?','?','?','?','?']]
for i in indices:
    general_h.remove(['?','?','?','?','?','?'])
print("\n final specific_h:",specific_h,sep="\n")
print("\n final general_h:",general_h,sep="\n")



sky,temp,humidity,wind,water,forecast,enjoy sport
sunny,warm,normal,strong,warm,same,yes
sunny,warm,high,strong,warm,same,yes
rainy,cloud,high,strong,warm,change,no
sunny,warm,high,strong,cool,change,yes

///////////////////////////////////////program 3/////////////////////////////////////////

import pandas as pd
import numpy as np
df=pd.read_csv("pro3.csv")
df
df.head()
df.tail()
df.describe()
df.info()
df.isnull().sum()
df.drop("name",axis=1,inplace=True)
df
df.drop(10,axis=0,inplace=True)
df
df["age"]=df["age"].fillna(df["age"].mean())
df
df["salary"]=df["salary"].fillna(df["salary"].max())
df
df.drop_duplicates()
x=np.array(df)[:,:-1]
x
y=np.array(df)[:,-1]
y
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct=ColumnTransformer(transformers=[('encoder',OneHotEncoder(),[0])],remainder="passthrough")
x=np.array(ct.fit_transform(x))
x
from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
y=le.fit_transform(y)
y
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
from sklearn.preprocessing import StandardScaler
st_x=StandardScaler()
x_train=st_x.fit_transform(x_train)
x_test=st_x.transform(x_test)
x_test
y_train
y_test



city,name,age,salary,eligible for bonus
mumbai,john,27,51000,yes
newyork,sam,27,48000,yes
mumbai,john,27,51000,yes
mumbai,ram,30,52000,no
newyork,ajay,,66000,no
tokyo,udgeeth,48,,yes
tokyo,sahaja,,51000,no
singapoor,rithesh,33,69000,no
newyork,rithvik,40,79000,yes
mumbai,srija,38,,yes
newyork,,,,
singapoor,ricky,35,38000,no
tokyo,mahesh,,56000,no
singapoor,jenifer,35,72000,no
newyork,peter,45,79000,yes
mumbai,charvi,31,81000,yes
singapoor,reyansh,37,49000,no

////////////////////////////////////program 4///////////////////////////////////////////////////

import pandas as pd
from collections import Counter
import math

tennis=pd.read_csv('pro4.csv')
print("\n given play tennis data set:\n\n",tennis)

def entropy(alist):
    c=Counter(x for x in alist)
    instances=len(alist)
    prob=[x/instances for x in c.values()]
    return sum([-p*math.log(p,2)for p in prob])

def information_gain(d,split,target):
    splitting=d.groupby(split)
    n=len(d.index)
    agent=splitting.agg({target:[entropy,lambda x:len(x)/n]})[target]
    agent.columns=['Entropy','observations']
    newentropy=sum(agent['Entropy']*agent['observations'])
    oldentropy=entropy(d[target])
    return oldentropy-newentropy

def id3(sub,target,a):
    count=Counter(x for x in sub[target])
    if len(count)==1:
        return next(iter(count))
    else:
        gain=[information_gain(sub,attr,target)for attr in a]
        print("\n Gain=",gain)
        maximum=gain.index(max(gain))
        best=a[maximum]
        print("\nBest attribute:",best)
        tree={best:{}}
        remaining=[i for i in a if i!=best]
        
        for val,subset in sub.groupby(best):
            subtree=id3(subset,target,remaining)
            tree[best][val]=subtree
        return tree

names=list(tennis.columns)
print("\n list of attributes:",names)
names.remove('PlayTennis')
print("\n predicting attributes:",names)

tree=id3(tennis,'PlayTennis',names)
print("\n\nthe resultant decision tree is :")
print(tree)



PlayTennis,Outlook,Temperature,Humidity,Wind
No,Sunny,Hot,High,Weak
No,Sunny,Hot,High,Strong
Yes,Overcast,Hot,High,Weak
Yes,Rain,Mild,High,Weak
Yes,Rain,Cool,Normal,Weak
No,Rain,Cool,Normal,Strong
Yes,Overcast,Cool,Normal,Strong
No,Sunny,Mild,High,Weak
Yes,Sunny,Cool,Normal,Weak
Yes,Rain,Mild,Normal,Weak
Yes,Sunny,Mild,Normal,Strong
Yes,Overcast,Mild,High,Strong
Yes,Overcast,Hot,Normal,Weak
No,Rain,Mild,High,Strong

////////////////////////////////////////program 5////////////////////////////////////////

from sklearn import datasets
iris=datasets.load_iris()
print(iris.target_names)
print(iris.feature_names)
X,y=datasets.load_iris(return_X_y=True)
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.30)
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
data=pd.DataFrame({'sepallength':iris.data[:,0],'sepalwidth':iris.data[:,1],
                  'petallength':iris.data[:,2],'petalwidth':iris.data[:,3],
                  'species':iris.target})
print(data.head())
clf=RandomForestClassifier(n_estimators = 2)
clf.fit(X_train , y_train)
y_pred=clf.predict(X_test)
from sklearn import metrics
print()
print("ACCURACY OF THE MODEL:",metrics.accuracy_score(y_test , y_pred))
clf.predict([[3,3,2,2]])
clf.predict([[6,6,6,6]])

///////////////////////////////////////////////////////////////////////////////////////////////