10/1/23, 11:18 PM Untitled1.

ipynb - Colaboratory
1 import pandas as pd
2 import matplotlib.pyplot as plt
3 import sklearn
4 import numpy as np
5

1 data = pd.read_csv("Data211.csv")
2 #Print top 5 rows of the dataframe
3 data.head()

X1 X2 X3 X4 X5 X6 X7 X8 Y1 Y2

0 0.98 514.5 294.0 110.25 7.0 2 0.0 0 15.55 21.33

1 0.98 514.5 294.0 110.25 7.0 3 0.0 0 15.55 21.33

2 0.98 514.5 294.0 110.25 7.0 4 0.0 0 15.55 21.33

3 0.98 514.5 294.0 110.25 7.0 5 0.0 0 15.55 21.33

4 0.90 563.5 318.5 122.50 7.0 2 0.0 0 20.84 28.28

1 X = data.iloc[:, :-1]
2 y = data.iloc[:, -1]

1 from sklearn.model_selection import train_test_split

2 X_test, X_train, y_train, y_test = train_test_split(X, y, test_size = 0.5, random_state = 0 )
3 print(X_test)
4
5

X1 X2 X3 X4 X5 X6 X7 X8 Y1
54 0.90 563.5 318.5 122.50 7.0 4 0.10 1 29.14
30 0.71 710.5 269.5 220.50 3.5 4 0.00 0 6.37
424 0.64 784.0 343.0 220.50 3.5 2 0.25 3 16.83
682 0.86 588.0 294.0 147.00 7.0 4 0.40 4 32.15
100 0.90 563.5 318.5 122.50 7.0 2 0.10 2 28.88
.. ... ... ... ... ... .. ... .. ...
763 0.64 784.0 343.0 220.50 3.5 5 0.40 5 17.88
192 0.98 514.5 294.0 110.25 7.0 2 0.10 4 24.38
629 0.90 563.5 318.5 122.50 7.0 3 0.40 3 34.95
559 0.71 710.5 269.5 220.50 3.5 5 0.40 1 14.58
684 0.82 612.5 318.5 147.00 7.0 2 0.40 4 28.93

[384 rows x 9 columns]

1 Train_data = pd.concat([X_train, y_train], axis = 'columns', #Join along the columns

2 names=['D1', 'D2', 'D3', 'D4', 'D5', 'D6', 'D7'])
3 Train_data.head()

X1 X2 X3 X4 X5 X6 X7 X8 Y1 Y2

661 0.66 759.5 318.5 220.50 3.5 3.0 0.4 3.0 15.18 NaN

122 0.74 686.0 245.0 220.50 3.5 4.0 0.1 2.0 10.32 NaN

113 0.79 637.0 343.0 147.00 7.0 3.0 0.1 2.0 37.26 NaN

14 0.82 612.5 318.5 147.00 7.0 4.0 0.0 0.0 16.95 NaN

529 0.98 514.5 294.0 110.25 7.0 3.0 0.4 1.0 32.26 NaN

1 Train_data.describe()
2 corr_mat = Train_data.corr(method ='pearson')
3 corr_mat

X1 X2 X3 X4 X5 X6 X7 X8 Y1 Y2

X1 1.000000 -0.991563 -0.200837 -0.870450 0.819848 -0.014718 -0.036640 -0.037592 0.594804 NaN

X2 -0.991563 1.000000 0.190741 0.883489 -0.853371 0.009437 0.037866 0.031705 -0.635506 NaN

X3 -0.200837 0.190741 1.000000 -0.291333 0.290551 -0.016808 -0.010377 0.030027 0.465589 NaN

X4 -0.870450 0.883489 -0.291333 1.000000 -0.970276 0.017218 0.041853 0.016568 -0.841494 NaN

X5 0.819848 -0.853371 0.290551 -0.970276 1.000000 -0.008448 -0.044356 -0.004967 0.877522 NaN

X6 -0.014718 0.009437 -0.016808 0.017218 -0.008448 1.000000 -0.099348 -0.013862 -0.025379 NaN

X7 -0.036640 0.037866 -0.010377 0.041853 -0.044356 -0.099348 1.000000 0.195659 0.245926 NaN

X8 -0.037592 0.031705 0.030027 0.016568 -0.004967 -0.013862 0.195659 1.000000 0.096695 NaN

Y1 0.594804 -0.635506 0.465589 -0.841494 0.877522 -0.025379 0.245926 0.096695 1.000000 NaN

Y2 NaN NaN NaN NaN NaN NaN NaN NaN NaN 1.0

1 plt.matshow(corr_mat)
2 plt.xticks(range(len(corr_mat.columns)), corr_mat.columns, rotation=90)
3 plt.yticks(range(len(corr_mat.columns)), corr_mat.columns)
4 plt.colorbar()
5 plt.show()

1 plt.scatter(X_train['X1'], y_train)
2 plt.title("Roof area vs heating load")
3 plt.xlabel("roof area")
4 plt.ylabel("heating load")
5 plt.plot()

[]

1 from sklearn import preprocessing

2 from sklearn import utils
3
4 lab_enc = preprocessing.LabelEncoder()
5 encoded = lab_enc.fit_transform(y_train)

1 from sklearn.preprocessing import StandardScaler

2 sc = StandardScaler()
3 X_train = sc.fit_transform(X_train)
4 X_test = sc.transform(X_test)

1 from sklearn.neighbors import KNeighborsRegressor

2 Reg = KNeighborsRegressor(n_neighbors=2)
3 Reg.fit(X_train, y_train)

▾ KNeighborsRegressor
KNeighborsRegressor(n_neighbors=2)

1 y_pred = Reg.predict(X_test)
2 print(y_pred)
3
4

https://colab.research.google.com/drive/1EEP1v692iITCRu4S7WZXI9moiEtSgFqt#scrollTo=RSZldCtVaRho&printMode=true 1/1