Machine learning : The basic Code which used for any model implementation to reduce the programmer thinking

Machine learning :

Libraries Importing

1Import Numpy as np:


This Libraries used for mathematical calculation and many equation to calculate easily.






2.Import Pandas as pd:


This Libraries used for Importing datasets and operation on data sets.it also contain some built in function for easy to transform data in some specific format
3.Import Matlibplot.pyplot as plot:


This Libraries used for scientific plotting.it used for representation of data in some specific format like tree ,pie ,graphs etc.

4.Libraries Slearn:


This Libraries used for Formatting data and transform the data in specific format.The some class of sklearn are OneHotEncoder ,Preprocessing.The Sklearn is used for data transform ,Scaling rang & finding missing data.




Data Processing

Pandas:


Used to import the data

pandas























Sklearn:

It best libraries for processing ,while this is used for #dummy create pasiing index # categorial data #missing data conditions

For Learning Sklearn

Sklearn : https://scikit-learn.org/stable/tutorial/index.html

Tensorflow:


Used Many Machine learning Model like face detection and mant thing

Tensorflow

# template is heavnly need and also feature scaling is not need for mant time but if required we used

import numpy as np

import matplotlib.pyplot as plot

import pandas as pd

#import the data sets

dataset = pd.read_csv('data.csv')

X = dataset.iloc[: , :-1].values

Y = dataset.iloc[: ,:3].values

#split the set to traning and test sets

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) # test size should be displayed

#scaling

from sklearn.preprocessing import StandardScaler

sc_X = StandardScaler()

X_train = sc_X.fit_transform(X_train)

X_test  = sc_X.transform(X_test)

# scale dumay vriable

Feature Scaling :

#feature scaling .. range is gavien like ages ,saleries. Ecludien Distane ... decrease the value to scale in limted range

# feature of scaling .. (standartlization )Xstand =X-mean(x)/standard deviation(x)  && (Normalization) Xnorm=X-min(x)/max(X)-min(X)

import numpy as mp

import matplotlib.pyplot as plot

import pandas as pd

#data processing

dataset = pd.read_csv('data.csv')

X = dataset.iloc[:,:-1].values

Y = dataset.iloc[:,3].values

#missing data conditions 

from sklearn.impute import SimpleImputer

simp = SimpleImputer(missing_values = 'NaN' , strategy = 'mean' )

simp = SimpleImputer().fit(X[:, 1:3])

X[: ,1:3] = simp.transform(X[: ,1:3])

print(X)

# categorial data

from sklearn.preprocessing import LabelEncoder ,OneHotEncoder

X = X.reshape(1,-3)

labelencoder_X = LabelEncoder()

X[:, 0]=labelencoder_X.fit_transform(X[:,0])

onehotencoder = OneHotEncoder(OneHotEncoder(categories='auto', sparse=False))

   #dummy create  pasiing index 

X = onehotencoder.fit_transform(X[0]).toarray()

labelencoder_Y = LabelEncoder()

Y= labelencoder_Y.fit_transform(Y)

#split the set to traning and test sets

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) # test size should be displayed

#scaling

from sklearn.preprocessing import StandardScaler

sc_X = StandardScaler()

X_train = sc_X.fit_transform(X_train)

X_test  = sc_X.transform(X_test)

print(X_train)

print(X_test)

# scale dumay vriable

I am GR,3+ years Exp of SEO, content writing, and keyword research ,software dev with skills in OS, web dev, Flask, Python, C++, data structures, and algorithms ,Reviews.