KNN.py

# -*- coding: utf-8 -*-
"""
Created on Mon Nov  9 11:25:00 2020

@author: Shreya
"""
import pandas as pd
import numpy as np

datainput = pd.read_csv('datafile.csv')

#preprocessing
X = datainput[['Crop', 'State', 'Cost of Cultivation (`/Hectare) A2+FL', 'Cost of Cultivation (`/Hectare) C2','Cost of Production (`/Quintal) C2' ]].values

from sklearn import preprocessing
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
#label encoder to categorical data 
labelencoder_X = preprocessing.LabelEncoder()
X[:,0] = labelencoder_X.fit_transform(X[:, 0])
X[:,1] = labelencoder_X.fit_transform(X[:, 1])

#One hot encoder 
columnTransformer = ColumnTransformer([('encoder', OneHotEncoder(),[0])], remainder='passthrough')   
x2 = np.array(columnTransformer.fit_transform(X), dtype = np.float) 

columnTransformer = ColumnTransformer([('encoder', OneHotEncoder(),[10])], remainder='passthrough')  
x3 = np.array(columnTransformer.fit_transform(x2), dtype = np.float) 

y = datainput.iloc[:,-1]

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import DecisionTreeRegressor
from sklearn import metrics
from sklearn import utils
X_train, X_test, y_train, y_test = train_test_split(x3, y, test_size=0.3, random_state=3)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

from sklearn import neighbors
from sklearn.metrics import mean_squared_error 
from math import sqrt
import matplotlib.pyplot as plt

rmse_val = [] #to store rmse values for different k
for K in range(20):
    K = K+1
    model = neighbors.KNeighborsRegressor(n_neighbors = K)

    model.fit(X_train, y_train)  #fit the model
    pred=model.predict(X_test) #make prediction on test set
    error = sqrt(mean_squared_error(y_test,pred)) #calculate rmse
    rmse_val.append(error) #store rmse values
    print('RMSE value for k= ' , K , 'is:', error)

curve = pd.DataFrame(rmse_val) #elbow curve 
curve.plot()

from sklearn.neighbors import KNeighborsClassifier

regressor = neighbors.KNeighborsRegressor(n_neighbors = 4)
regressor.fit(X_train, y_train)

# Predicting the Test set results
y_pred = regressor.predict(X_test)
error = sqrt(mean_squared_error(y_test,y_pred)) #calculate rmse
rmse_val.append(error)

print(error)