Question

I am writing this machine learning code (classification) to clssify between two classes. I started by having one feature to capture for all my images.

for example:

class A=[(4295046.0, 1), (4998220.0, 1), (4565017.0, 1), (4078291.0, 1), (4350411.0, 1), (4434050.0, 1), (4201831.0, 1), (4203570.0, 1), (4197025.0, 1), (4110781.0, 1), (4080568.0, 1), (4276499.0, 1), (4363551.0, 1), (4241573.0, 1), (4455070.0, 1), (5682823.0, 1), (5572122.0, 1), (5382890.0, 1), (5217487.0, 1), (4714908.0, 1), ...etc]

first number is the data and the second number is the label

class B=[(7179088.0, 0), (7144249.0, 0), (6806806.0, 0), (5080876.0, 0), (5170390.0, 0), (5694876.0, 0), (6210510.0, 0), (5376014.0, 0), (6472171.0, 0), (7112956.0, 0), (7356507.0, 0), (7418046.0, 0), (7975884.0, 0), (7862043.0, 0), (7627016.0, 0), (7778397.0, 0), (7175463.0, 0), (7347721.0, 0), (5646602.0, 0), (5357049.0, 0), ....etc]

the number is acting as a feature to classify the two type? how should the data loook like if I am introducing another feature?

Answer 1

#CODE
import pandas as pd

import numpy as np

from sklearn.model_selection import train_test_split
A=[(4295046.0, 1), (4998220.0, 1), (4565017.0, 1),
(4078291.0, 1), (4350411.0, 1), (4434050.0, 1),
(4201831.0, 1), (4203570.0, 1), (4197025.0, 1),
(4110781.0, 1), (4080568.0, 1), (4276499.0, 1),
(4363551.0, 1), (4241573.0, 1), (4455070.0, 1),
(5682823.0, 1), (5572122.0, 1), (5382890.0, 1), (5217487.0,1), (4714908.0, 1), (4697137.0, 1),(4737784.0, 1),
(4648881.0, 1), (4591211.0, 1), (4750706.0, 1),
(5067788.0, 1), (7392115.0, 1), (7024501.0, 1),
(6590118.0, 1), (6260326.0, 1), (6001223.0, 1),
(5513267.0, 1), (5684732.0, 1), (4092011.0, 1),
(6634798.0, 1), (6885369.0, 1), (2854799.0, 1),
(2642866.0, 1), (2591293.0, 1), (2345370.0, 1),
(2353085.0, 1), (2598480.0, 1), (3996284.0, 1),
(7536032.0, 1), (7338023.0, 1), (7561037.0, 1),
(7529364.0, 1), (7577504.0, 1), (7353176.0, 1),
(4057898.0, 1), (4143981.0, 1), (3899129.0, 1),
(3830584.0, 1), (3557377.0, 1), (3125518.0, 1), (3197039.0,1), (3109404.0, 1), (3024219.0, 1), (3066759.0, 1),
(2726363.0, 1), (3507626.0, 1), (2531828.0, 1),
(2330385.0, 1), (2317570.0, 1), (2444669.0, 1),
(2513998.0, 1), (2624739.0, 1), (3555578.0, 1),
(2582228.0, 1), (4404128.0, 1), (4307425.0, 1),
(4188310.0, 1), (2460042.0, 1), (4387062.0, 1),
(2162785.0, 1), (2168945.0, 1), (2304868.0, 1),
(2437261.0, 1), (3557410.0, 1), (3830618.0, 1),
(3550021.0, 1), (3588758.0, 1), (3447567.0, 1),
(3559924.0, 1), (3284499.0, 1), (3595260.0, 1),
(4494963.0, 1), (4294039.0, 1), (3849395.0, 1),
(3620279.0, 1), (3406951.0, 1), (3578885.0, 1),
(3763810.0, 1), (3820821.0, 1)]
B=[(7179088.0, 0), (7144249.0, 0), (6806806.0, 0),
(5080876.0, 0), (5170390.0, 0), (5694876.0, 0),
(6210510.0, 0), (5376014.0, 0), (6472171.0, 0),
(7112956.0, 0}, (7356507.0, 0}, (7418046.0, 0),
(7975884.0, 0), (7862043.0, 0), (7627016.0, 0),
(77783970, 0), (7175463.0, 0), (7347721.0, 0),
(5646602.0, 0), (5357049.0, 0), (6435755.0, 0),
(7254820.0, 0), (7509701.0, 0), (7588029.0, 0),
(7491507.0, 0), (7505240.0, 0), (7650181.0, 0),
(7574974.0, 0), (7579726.0, 0), (7444229.0, 0),
(3777032.0, 0}, (7379626.0, 0), (7184128.0, 0),
(73209110, 0), (7425228.0, 0), (7489048.0, 0),
(7145778.0, 0), (7754034.0, 0), (8635490.0, 0),
(8798277.0, 0), (8067185.0, 0), (8205319.0, 0),
(8908959.0, 0), (9153481.0, 0), (9180030.0, 0),
(9183460.0, 0), (9212517.0, 0), (9055663.0, 0),
(9053709.0, 0), (9103067.0, 0), (8889903.0, 0),
(8328604.0, 0), (8475442.0, 0), (8499221.0, 0),
(8752169.0, 0), (8779133.0, 0), (8756789.0, 0),
(8990732.0, 0), (9027381.0, 0), (9090035.0, 0},
(9343846.0, 0), (9518609.0, 0), (9435149.0, 0),
(9365842.0, 0), (9395256.0, 0), (4381880.0, 0),
(4749338.0, 0), (5296143.0, 0), (5478942.0, 0),
(5610865.0, 0), (5514997.0, 0), (5381010.0, 0),
(5090416.0, 0), (4663958.0, 0), (4804526.0, 0),
(4743107.0, 0), (4898914.0, 0), (6018503.0, 0),
(5778240.0, 0), (5741893.0, 0), (4632926.0, 0),
(5208486.0, 0), (5633403.0, 0), (5699410.0, 0),
(5748260.0, 0), (5869260.0, 0), (5589575.0, 0),
(5627535.0, 0), (5551501.0, 0), (5467609.0, 0),
(5513782.0, 0), (5491950.0, 0), (5887072.0, 0),
(6419620.0, 0), (6625864.0, 0), (6645778.0, 0),
(6580741.0, 0), (6152337.0, 0), (5991092.0, 0),
(5847561.0, 0), (5718127.0, 0), (5971544.0, 0),
(6031962.0, 0), (5873358.0, 0), (6135263.0, 0),
(2886886.0, 0), (3855637.0, 0}, (7817578.0, 0),
(3747685.0, 0), (7886519.0, 0), (8277473.0, 0),
(8284216.0, 0), (8284850.0, 0), (7753420.0, 0),
(7825824.0, 0), (3808486.0, 0), (3809493.0, 0),
(3808122.0, 0), (3637373.0, 0), (3556258.0, 0),
(3487921.0, 0), (3475961.0, 0), (3468375.0, 0),
(3410898.0, 0), (3965656.0, 0), (4175368.0, 0),
(4602949.0, 0), (4718392.0, 0), (4876949.0, 0),
(5129132.0, 0), (5110047.0, 0), (50996320, 0),
(4935172.0, 0), (4303854.0, 0)]

data=[*A,*B]

x = [[each[0]] for each in data]

y = [[each[1]] for each in data]

print (len(x), len(y))

x_train, x_test, y_train, y_test = train_test_split(x, y,test_size=0.2, random_state=42)

print (len(x_train), len(x_test))

print (len(y_train), len(y_test))

from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier(n_estimators=100,max_depth=2, random_state=0)

clf-fit(x_train, y_train)

clf.score(x_test,y_test)

#convert feature 1 from list to int

temp=[]

for ele in x:

temp.extend(ele)

xX=np.array(temp)

y=np.array(y)

#To add new features to data using pandas DataFrame
makes the task easier for us
df=pd.DataFrame(x)
df['y']=y
df.columns=['f1','y']
df.head()

#Adding new feature
df['f2']=df['f1']*3
df.head()