Data Preprocessisng:-

1. Get Data Set

2. Import important libraries:-

​ import numpy as np :- for number calculations and array manupulation

​ import matplotlib.pyplot as plt:- for pictorial representation of results

​ import pandas as pd:- read and manupulate the data , for series operations

3. Import dataset:- (sir’s example)

​ data.csv/xls
​
​ dataset=pd.read_csv(‘Data.csv’)

​ > create matrix of all independent variables(sir’s example)

​ ​ x = datset.iloc[:, :-1].values
​
​ > create matrix of dependent variables(sir’s example)
​ ​ y = datset.iloc[:, 3].values

4. Handaling missing values

​ taking care of missing data from :-
​ > from sklearn.preprocessing import Imputer (sklearn is a ML lib for multiple
jobs,
​ ​ ​ ​ ​ ​ ​ Imputer use to find the missing values
​ ​ ​ ​ ​ ​ ​ ​ ​ rememberer caps I)
​
​ > imputer = Imputer(missing_values =’NaN’,strategy = ’mean’, axis=0)
​ ​ imputer = imputer.fit(x[:,1:3])
​
>x[:,1:3] = imputer.transform(x[:,1:3])

5. Categorical Data:-
​ Encoding Categorical Data:
​ #Encoding the independent variable:-
​ ​ > from sklearn.preprocessing import LabelEncoder,OneHotEncoder
​ ​ ​ ​ ​ (LabelEncoder will give numbers to entities of same
category)
​ ​
​ ​ > labelencoder_x = LabelEncoder()
​ ​ x[:,0] = labelencoder_x.fit_transform(x[:,0])(here it will enocde the first
column ​ ​ ​ ​ ​ ​ ​ ​ ​ values as 0,1,2...)
​ ​
​ ​ > onehotencoder = OneHotEncoder(categorical_features=[0])

​ ​
​ ​ > x=onehotencoder.fit_transform(x).toarray() (to encode x in terms of o’s and
1’s and ​ ​ ​ ​ ​ ​ ​ ​ ​ other values in
exponential form)
​ ​ x
​ ​
​ ​ >labelencoder_y=LabelEncoder() (encoding y)
​ ​ y = labelencoder_y.fit_transform(y)
6. Spliting Training and Test Data:-
​
​ > from sklearn.cross_validation import train_test_split
note:- (cross validation is library for spliting the whole data set in training and testing
data..... inside which we call the train and test
class for spliting the data)​
​
​ >x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state = 0)
​ ​ (splits the whole data set for 80% data for tarining, 20% data for testing,,
​ ​ random state maintains the consistency in the train and test data,if not then
every ​​ time it takes duffrent set if values)

​ ​ try to keep the train test in between the range of 20-30% as <20 results in
overfitting and more than 30 leads to error

7. Future scaling:- (is used to scale large values in small space.. like putting the two
numbers and the square of their diuffrence in the same graph)
​ (Note:- all values will be scaled between -1 to +1)
​
​ > from sklearn.preprocessing import Standard Scaler
​ sc_x = Standard Scaler​
​ x_train = sc_x.fit_transform(x_train) #fit.transform-- use only for training data
​ x_test = sc_x.transform(x_test)
​ ## x_train=always a dependent variable
​ ## standard scaler is a class that scales all the values based on volume of ,model...
​ ## fit()- generate learning model parameters from training data (only makes
machine to ​ ​ ​ ​ learn) going to make the object ready
​ ##transform()-- applied upon model to generate transform data set..

​ Mnote:_ fit_transform() can only be applied on standard scaler functions

**k-nn algorithm:-
from sklearn.neighbors import KneighborsClassifier
classifier = KneighborsClassifier(n_neighbors=5, metric=’minkowski’, p=2)
classifier.fit(X_train,Y_train)
-------till here machine if fit with trianing data and machines learns with training data----

## in sklearn neighbors is a library in which we have kneighbors classifiers

## kneighbors takes some values=== n-neighbors are number of neighbours... a prime
number
​ ​ ​ ​ ​ metrics == defines the type of method being used
​ ​ ​ ​ ​ p=2 means using euclidean distance
------ for testing and predictiong------
y_pred = classifier.predict(X_test) ## predicts only on x_test values given before
y_pred

**making the confusion matrix----

from sklearn.metrics import confusion_matrix​ ​ ## confusion_matrix is a fnc

cm = confusion_matrix(y_test,y_pred)
cm
gives out a confusion matrix with [TP,FP,FN,TN] format/....

*STEP 8:- Visualizing the Training and Test data set results

from matplotlib.colors import ListedColormap

x_set,y_set=x_train,y_train

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha=0.75,cmap=ListedColormap((‘red’,’green’)))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.uniquely(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap((‘red’,’green’))(i),label=j)
plt.title(‘K-NN(Training set)’)
plt.xlabel(‘Age’)
plt.yalbel(‘Estimnated sAlary’)
plt.legend()
plt.show()

**
*STEP 9:- Visualizing the Training and Test data set results

from matplotlib.colors import ListedColormap

x_set,y_set=x_train,y_train
x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha=0.75,cmap=ListedColormap((‘red’,’green’)))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.uniquely(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap((‘red’,’green’))(i),label=j)
plt.title(‘K-NN(Training set)’)
plt.xlabel(‘Age’)
plt.yalbel(‘Estimnated sAlary’)
plt.legend()
plt.show()

**decision treee:--

dataset=pd.read_csv('Social_Network_Ads.csv')
x = dataset.iloc[:,[2,3]].values
y = dataset.iloc[:, 4].values

from sklearn.cross_validation import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25,random_state = 0)

from sklearn.preprocessing import StandardScaler

sc_x = StandardScaler()
x_train = sc_x.fit_transform(x_train)
x_test = sc_x.transform(x_test)

from sklearn.tree import DecisionTreeClassifier

classifier = DecisionTreeClassifier(criterion = 'entropy',random_state=0)
classifier.fit(x_train,y_train)

y_pred = classifier.predict(x_test)

from sklearn.metrics import confusion_matrix

cm = confusion_matrix(y_test,y_pred)
cm

training plot:-
from matplotlib.colors import ListedColormap
x_set,y_set=x_train,y_train

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha = 0.75,cmap = ListedColormap(('red','green')))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.unique(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap(('red','green'))(i),label=j)
plt.title('Decison Tree(Training set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()

Test plot :--

from matplotlib.colors import ListedColormap

x_set,y_set=x_test,y_test

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha = 0.75,cmap = ListedColormap(('red','green')))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.unique(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap(('red','green'))(i),label=j)
plt.title('Decison Tree(Test set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()
***Naive Bayes
dataset=pd.read_csv('Social_Network_Ads.csv')
x = dataset.iloc[:,[2,3]].values
y = dataset.iloc[:, 4].values

from sklearn.cross_validation import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25,random_state = 0)

from sklearn.preprocessing import StandardScaler

sc_x = StandardScaler()
x_train = sc_x.fit_transform(x_train)
x_test = sc_x.transform(x_test)

from sklearn.naive_bayes import GaussianNB

classifier = GaussianNB()
classifier.fit(x_train,y_train)

y_pred = classifier.predict(x_test)

from sklearn.metrics import confusion_matrix

cm = confusion_matrix(y_test,y_pred)
cm

training plot:-
from matplotlib.colors import ListedColormap

x_set,y_set=x_train,y_train

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha = 0.75,cmap = ListedColormap(('red','green')))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.unique(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap(('red','green'))(i),label=j)
plt.title('Naive Bayes(Training set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()
Test plot :--
from matplotlib.colors import ListedColormap

x_set,y_set=x_test,y_test

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha = 0.75,cmap = ListedColormap(('red','green')))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.unique(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap(('red','green'))(i),label=j)
plt.title('Naive Bayes(Test set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()

**Random forest
dataset=pd.read_csv('Social_Network_Ads.csv')
x = dataset.iloc[:,[2,3]].values
y = dataset.iloc[:, 4].values

from sklearn.cross_validation import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25,random_state = 0)

from sklearn.preprocessing import StandardScaler

sc_x = StandardScaler()
x_train = sc_x.fit_transform(x_train)
x_test = sc_x.transform(x_test)

from sklearn.ensemble import RandomForestClassifier

classifier = RandomForestClassifier(n_estimators = 10,criterion =
'entropy',random_state=0)
classifier.fit(x_train,y_train)

y_pred = classifier.predict(x_test)

from sklearn.metrics import confusion_matrix

cm = confusion_matrix(y_test,y_pred)
cm
from matplotlib.colors import ListedColormap

x_set,y_set=x_train,y_train

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha = 0.75,cmap = ListedColormap(('red','green')))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.unique(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap(('red','green'))(i),label=j)
plt.title('Naive Bayes(Training set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()

from matplotlib.colors import ListedColormap

x_set,y_set=x_test,y_test

x1,x2=
np.meshgrid(np.arange(start=x_set[:,0].min()-1,stop=x_set[:,0].max()+1,step=0.01),np.ara
nge(start=x_set[:,1].min()-1,stop=x_set[:,1].max()+1,step=0.01))

plt.contourf(x1,x2,classifier.predict(np.array([x1.ravel(),x2.ravel()]).T).reshape(x1.shape),al
pha = 0.75,cmap = ListedColormap(('red','green')))

plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())

for i,j in enumerate(np.unique(y_set)):

​
plt.scatter(x_set[y_set==j,0],x_set[y_set==j,1],c=ListedColormap(('red','green'))(i),label=j)
plt.title('Naive Bayes(Test set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()

Linear Regression:-
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

dataset=pd.read_csv('Salary_Data.csv')
x = dataset.iloc[:,:-1].values
y = dataset.iloc[:,1].values

from sklearn.cross_validation import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25,random_state = 0)

from sklearn.linear_model import LinearRegression

regressor = LinearRegression()
regressor.fit(x_train,y_train)

y_pred = regressor.predict(x_test)

plt.scatter(x_train,y_train, color='red')
plt.plot(x_train,regressor.predict(x_train),color = 'blue')
plt.title('sal vs exp (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimnated sAlary')
plt.legend()
plt.show()