# importing relevant libraries import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns sns.set() from sklearn.linear_model import LinearRegression from sklearn.model_selection import train_test_split from sklearn.metrics import mean_squared_error

data = pd.read_csv('real_estate.csv') data.head()

x = data[['size','year']] y = data['price']

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

#conversion of x_train using a function which fits (figures out the params) then normalises. #Whilst the x_test conversion just transforms, using the same params that it learned from the train data. from sklearn.preprocessing import StandardScaler scaler = StandardScaler() x_train = scaler.fit_transform( x_train ) x_test = scaler.transform( x_test )

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

reg.score(x_test,y_test)

# coefficeints of the trained model print('Coefficient:', reg.coef_)

# intercept of the model print('Intercept:', reg.intercept_)

## Prepare the data for Visualization x_surf, y_surf = np.meshgrid(np.linspace(min(data['size']), max(data['size']), 100),np.linspace(min(data['year']), max(data['year']), 100)) onlyX = pd.DataFrame({'size': x_surf.ravel(), 'year': y_surf.ravel()}) fittedY=reg.predict(onlyX) ## convert the predicted result in an array fittedY=np.array(fittedY) fittedY

# Visualize the Data for Multiple Linear Regression from mpl_toolkits.mplot3d import Axes3D fig = plt.figure(figsize=(20,10)) ### Set figure size ax = fig.add_subplot(111, projection='3d') ax.scatter(data['size'],data['year'],data['price'],c='red', marker='o', alpha=0.5) ax.plot_surface(x_surf,y_surf,fittedY.reshape(x_surf.shape), color='b', alpha=0.3) ax.set_xlabel('Size') ax.set_ylabel('Year') ax.set_zlabel('Price') plt.show()

# code for visualizing SLRM #plt.scatter(data['x'], data['y']) #plt.plot(data['x'], reg.predict(x))

# Root Mean Squared Error on training dataset import math print('RMSE on train dataset : ', math.sqrt(mean_squared_error(y_train,reg.predict(x_train))))

# Root Mean Squared Error on testing dataset print('RMSE on test dataset : ', math.sqrt(mean_squared_error(y_test,reg.predict(x_test))))

from sklearn.preprocessing import PolynomialFeatures poly = PolynomialFeatures(degree = 4) x_poly = poly.fit_transform(x) poly.fit(x_poly, y) lin2 = LinearRegression() lin2.fit(x_poly, y)

import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.metrics import confusion_matrix

bank_data = pd.read_csv('Bank_data.csv') bank_data.head()

# Removes the index column b_data = bank_data.drop(['Unnamed: 0'], axis = 1) # We use the map function to change any 'yes' values to 1 and 'no'values to 0. b_data['y'] = b_data['y'].map({'yes':1, 'no':0}) b_data

X = b_data[['interest_rate','credit','march','previous','duration']] Y = b_data['y']

X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.2)

model = LogisticRegression() model.fit(X_train,Y_train)

#code for visualizing simple logistic regression # plt.scatter(x, y) # plt.plot(x, model.predict(x))

model.score(X_test,Y_test)

confusion_matrix(Y_test,model.predict(X_test))

from sklearn.metrics import mean_absolute_error print(mean_absolute_error(y_train,reg.predict(x_train)))

print(mean_absolute_error(y_test,reg.predict(x_test)))

##ENSEMBLE METHOD FOR LOGISTIC REGRESSION MODEL USED ABOVE from sklearn.ensemble import GradientBoostingClassifier from sklearn.metrics import accuracy_score #Create the object of the GradientBoosting Classifier model mod = GradientBoostingClassifier(n_estimators=100,max_depth=5) # fit the model with the training data mod.fit(X_train.astype('int'),Y_train.astype('int')) # predict the target on the train dataset predict_train = mod.predict(X_train) # Accuray Score on train dataset accuracy_train = accuracy_score(Y_train.astype('int'),predict_train) print('\naccuracy_score on train dataset : ', accuracy_train) # predict the target on the test dataset predict_test = mod.predict(X_test) # Accuracy Score on test dataset accuracy_test = accuracy_score(Y_test.astype('int'),predict_test) print('\naccuracy_score on test dataset : ', accuracy_test)