GenerationData.py
6.36 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
import numpy as np
import pandas as pd
import statistics
import random
#from distfit import distfit
import csv
#import math
from scipy.special import expit
class Generator:
def __init__(self, base):
self.base=base
def logit_Normal(self, x):
return 1/(1+np.exp(-x))
#Generation of dataset with grade and time for 15 questions and 5 complexity levels
def generationDatasetComplexities(self):
tbase=pd.DataFrame()
#Number of complexity levels
#sigma_grade=1.2#Initial
#mu_grade=0#initial
sigma_grade=0.5
mu_grade=1.5
sigma_time=1.7
mu_time=30
for rows in range(5):#5
tlist=[]
#Number of questions
for ncomp in range(15):#15 #3 for initial
if ncomp < 10:#Simulate mistakes in complexity level 1 first 3 questions
cgrade2=self.logit_Normal(np.random.normal(-1, 0.2, 700))
#if rows == 0 and ncomp < 10:#Simulate mistakes in complexity level 1 first 3 questions
# omu_grade=mu_grade
# mu_grade=-2
#if rows == 3 and ncomp < 3 :#Simulate mistakes in complexity level 3 first 3 questions
# omu_grade=mu_grade
# mu_grade=-1
else:
cgrade2=self.logit_Normal(np.random.normal(mu_grade, sigma_grade, 700))
#Number of questions (grade, time)
cgrade=self.logit_Normal(np.random.normal(mu_grade, sigma_grade, 300))
cgrade=np.append(cgrade, cgrade2)
cgrade=cgrade*10
ctime=np.random.normal(mu_time, sigma_time, 1000)
#vcomp=np.ones(len(vgrade))*(ncomp+1)
result = [cgrade.tolist(), ctime.tolist()]
tbase[len(tbase.columns)]=cgrade
tbase[len(tbase.columns)]=ctime
#omu_grade+=0.5
mu_grade-=0.2
sigma_grade+=0.08
tbase.to_csv("data.csv", sep=" ")
#Generation of dataset with mean of grade and mean of time for 15 questions and 10 sub-competences
def generationDatasetMeanSubCompetences(self):
tbase=[]
#Number of rows to generate
for rows in range(1000):
sigma_grade=1.7
mu_grade=5
sigma_time=1.7
mu_time=30
tlist=[]
#Number of sub-competences
for ncomp in range(10):
vgrade=[]
vtime=[]
#Number of questions (grade, time)
for i in range(15):
cgrade=np.random.normal(mu_grade, sigma_grade, 1)[0]
vgrade.append(cgrade)
ctime=np.random.normal(mu_time, sigma_time, 1)[0]
vtime.append(ctime)
nmu_grade=np.mean(vgrade)
nmu_time=np.mean(vtime)
vcomp=np.ones(len(vgrade))*(ncomp+1)
result = [np.mean(vgrade), np.mean(vtime)]
tlist=tlist + result
mu_grade=np.random.normal(nmu_grade, 0.5, 1)[0]
mu_time=np.random.normal(nmu_time, 0.5, 1)[0]
sigma_grade=(abs(mu_grade-nmu_grade))*0.4
sigma_time=(abs(mu_time-nmu_time))*0.4
#print(tlist)
tbase.append(tlist)
#print(tbase)
#Write the csv file
with open("dataMean.csv", "w", newline="") as f:
writer=csv.writer(f)
writer.writerows(tbase)
def generation(self):
vlambda = 0.5
lbase=self.base
#print(lbase)
for i in range(100):
element1=lbase.sample()
element1=vlambda*np.array(element1)
element2=lbase.sample()
element2=(1.0-vlambda)*np.array(element2)
#print(element1)
#print(element2)
#print(element1[0]+element2[0])
elementN=pd.DataFrame(element1+element2)
#print(elementN)
#Concatenate self.base and elementN
return self.base
#print(x)
#Generation with white noise
def generation3(self):
mu, sigma = 0, 0.1
x=[sum(self.base.iloc[i,:]) for i in range(21)]
#print(x)
for i in range(1000):
element=self.base.sample()
noise=np.random.normal(mu, sigma, [1, element.shape[1]])
nbase=[self.base, element+noise]
self.base=pd.concat(nbase)
x=[sum(self.base.iloc[i,:]) for i in range(21)]
return self.base
#print(x)
def detection(self, data):
dfit=distfit()
dfit.fit_transform(data)
print(dfit.summary)
#Generation with detection of distribution for each column
def generation2(self):
dfit=distfit()
lbase=np.array(self.base)
newData=[]
for vindex in range(lbase.shape[1]):
#print("Column: ",lbase[:,vindex])
dfit.fit_transform(lbase[:,vindex])
sigma=dfit.model['scale']
nrand=dfit.generate(1)
newData.append(nrand)
lbase=lbase[(lbase[:,vindex] < (nrand + (sigma/1.0))) & (lbase[:,vindex] > (nrand - (sigma/1.0)))]
print(newData)
self.base.loc[len(self.base.index)]=newData
print(self.base.corr())
#Generation with normal distribution
def generation0(self):
lbase=self.base
print(lbase.corr())
#print(lbase[lbase[20].values==0].corr())
#print(lbase[lbase[20].values==0].iloc[1:100,:].corr())
for n in range(100):
vindex=0
newData=[]
lbase=self.base
for vindex in range(21):
#mu=statistics.median(self.base[vindex])
mu=statistics.mean(lbase[vindex])
sigma=statistics.stdev(lbase[vindex])
nrand=np.random.normal(mu, sigma, 1)[0]
#print(mu, " ", sigma, nrand)
#print(self.base.head())
lbase=lbase[(lbase[vindex].values < (nrand + (sigma/100.0))) & (lbase[vindex].values > (nrand - (sigma/100.0)))]
newData.append(nrand)
#print(lbase)
#print(newData)
self.base.loc[len(self.base.index)]=newData
print(self.base.corr())
g=Generator([])
#g.detection(data)
g.generationDatasetComplexities()
#g.generationDatasetMeanSubCompetences()