adding linear regression folder & scripts

2018/linear_regression/.~lock.creature_data_nrs.csv#

+,ana,anagram,16.11.2018 17:12,file:///home/ana/.config/libreoffice/4;
\ No newline at end of file

2018/linear_regression/.~lock.test_data_nrs.csv#

+,ana,anagram,16.11.2018 17:03,file:///home/ana/.config/libreoffice/4;
\ No newline at end of file

2018/linear_regression/creature_data.csv

+creature,distance,score
+interesting,0,9
+noble,0,8
+noble,1,8
+unfashioned,0,3
+human,0,5
+helpless,0,2
+pictured,2,5
+guilty,5,1
+yellow,3,5
+alive,11,8
+little,0,4
+unsocial,3,3
+happy,0,9
+capable,0,9
+pretended,8,3
+happy,0,9
+capable,0,9
+human,0,5
+unfit,0,2
+bound,4,2
+mild,5,6
+most,6,6
+fallen,11,2
+favourable,3,6
+desert,10,4
+eternal,3,7
+speedy,6,5
+happy,8,9
+young,0,5
+fair,0,9
+excellent,0,10
+lovely,0,10
+lovely,0,10
+high,1,5
+omnipotent,4,8
+perfect,0,10
+lovely,0,10
+amiable,0,8
+deserted,0,2
+excellent,0,10
+human,0,5
+generous,30,9
+little,0,4
+beautiful,0,9
+whole,7,8
+another,1,5
+fine,1,6
+inaccessible,18,3
+long,15,5
+whole,8,6
+tremulous,30,2
+greater,13,8
+future,2,5
+insuperable,6,3
+half finished,0,3
+shuddering,6,2
+human,0,5
+angelic,2,7
+every,0,5
+purest,0,8
+future,2,5
+every,6,5
+impenetrable,7,5
+glorious,0,10
+useful,3,8
+extensive,4,7
+rational,0,5
+first,0,6
+same,0,5

2018/linear_regression/creature_data_nrs.csv

+DISTANCE,VALUEADJ
+0,9
+0,8
+1,8
+0,3
+0,5
+0,2
+2,5
+5,1
+3,5
+11,8
+0,4
+3,3
+0,9
+0,9
+8,3
+0,9
+0,9
+0,5
+0,2
+4,2
+5,6
+6,6
+11,2
+3,6
+10,4
+3,7
+6,5
+8,9
+0,5
+0,9
+0,10
+0,10
+0,10
+1,5
+4,8
+0,10
+0,10
+0,8
+0,2
+0,10
+0,5
+30,9
+0,4
+0,9
+7,8
+1,5
+1,6
+18,3
+15,5
+8,6
+30,2
+13,8
+2,5
+6,3
+0,3
+6,2
+0,5
+2,7
+0,5
+0,8
+2,5
+6,5
+7,5
+0,10
+3,8
+4,7
+0,5
+0,6
+0,5

2018/linear_regression/monster_data.csv

+ADJECTIVE,VALUEADJ,DISTANCE
+miserable,0,0
+more,7,4
+poor,1,11
+unremitting,6,14
+last,5,13
+daily,6,3
+each,5,2
+abhorred,0,0
+bitterest,1,8
+all,5,7
+hideous,1,1
+detestable,0,0
+ugly,3,0
+hideous,1,0
+true,9,3
+deadly,1,20
+fond,9,7
+remote,4,16
+firm,5,9
+sanguinary,1,3
+tormented,2,9
+clouded,4,3
+dearest,10,9
+inevitable,3,5
+magic,8,2
+fiendish,1,7
+miserable,1,5
+mistaken,3,16
+gigantic,9,0
+greater,8,8
+connected,8,2
+wild,9,3

2018/linear_regression/monster_data_nrs.csv

+VALUEADJ,DISTANCE
+0,0
+7,4
+1,11
+6,14
+5,13
+6,3
+5,2
+0,0
+1,8
+5,7
+1,1
+0,0
+3,0
+1,0
+9,3
+1,20
+9,7
+4,16
+5,9
+1,3
+2,9
+4,3
+10,9
+3,5
+8,2
+1,7
+1,5
+3,16
+9,0
+8,8
+8,2
+9,3

2018/linear_regression/testing_frankenstein.py

+# -*- coding: utf-8 -*-
+# following this manual: https://towardsdatascience.com/linear-regression-using-python-ce21aa90ade6
+# using simple linear regression, trying to predict a continuous variable
+
+import pandas as pd
+import numpy as np
+import tkinter 
+import matplotlib.pyplot as plt   #Data visualisation libraries 
+import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+
+
+# import data
+test_data = pd.read_csv('creature_data_nrs.csv')
+
+# look at data
+# test_data.head()
+# test_data.info()
+# test_data.describe()
+# test_data.columns
+
+# shows all the data in graphs
+#graph1 = sns.pairplot(test_data)
+#plt.show()
+
+# shows the histogram to see the distribution of the target variable
+# graph2 = sns.distplot(test_data['VALUEADJ'])
+# plt.show()
+
+# find the correlation between variables in dataset
+#correlation = test_data.corr()
+
+# Create heatmap
+# The black colour represents that there is no linear relationship between the two variables. 
+# A lighter shade shows that the relationship between the variables is more linear.
+# graph3 = sns.heatmap(correlation)
+# plt.show()
+
+# Split data in training data (independent variable / distance) & labels (predicted variable / positivity rate adj)
+X = test_data[['DISTANCE']]
+y = test_data[['VALUEADJ']]
+
+# Split data into train & test data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=101)
+
+# define model Linear Regression
+model = LinearRegression()
+
+# train model with the training data
+model.fit(X_train,y_train)
+
+# predictions check
+predictions = model.predict(X_test)
+
+# visualise predictions
+# graph4 = plt.scatter(y_test,predictions)
+# plt.show()
+
+# Returns the coefficient of determination R^2 of the prediction.
+scores = model.score(X, y)
+print(scores)
+
+# Plot outputs
+plt.scatter(X_test, y_test,  color='black')
+plt.plot(X_test, predictions, color='blue', linewidth=3)
+
+plt.xticks(())
+plt.yticks(())
+
+plt.show()
\ No newline at end of file