AnalyticsCal-Classroom/Synthetic_data_gen.py at master · AnalyticsCal/AnalyticsCal-Classroom · GitHub

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
import openpyxl
import  array
import matplotlib.pylab as plt
import math
import random
import statistics


path = "Khanapur_Flows.xlsx"

column_name = "Discharge"

wb = openpyxl.load_workbook(path)
sheet = wb.active

discharge = array.array("f",[])

for j in range(1, sheet.max_column + 1):
    if (sheet.cell(row=1, column=j).value == column_name):

        for k in range(2, sheet.max_row + 1):
            discharge.append(sheet.cell(k, j).value)


print(len(discharge))
########################################################################################################
def monthly_mean(discharge):

    sum = [0]*12

    for i in range(12):
        count = 0
        for j in range(i,len(discharge),12):
            sum[i] += discharge[j]
            count += 1


        sum[i] = sum[i] / count
        #print(sum[i])

    return sum

#print(monthly_mean(discharge))
########################################################################################################
def standard_deviation(discharge, month_mean):
    deviation = [0]*12

    for i in range(12):
        count = 0
        for j in range(i, len(discharge), 12):

            deviation[i] += (discharge[j] - month_mean[i])*(discharge[j] - month_mean[i])
            count += 1

        deviation[i] =  math.sqrt(deviation[i] / count)

    return deviation


#print(standard_deviation(discharge, monthly_mean(discharge)))
########################################################################################################
def correlation_coefficient(discharge, month_mean, monthly_deviation):
    correlation = [0]*12
    count = 0
    for i in range(0, len(discharge), 12):

        correlation[0] += ((discharge[i] - month_mean[0]) * (discharge[i + 11] - month_mean[11]))
        count += 1

    correlation[0] = correlation[0] / count
    correlation[0] = correlation[0] / (monthly_deviation[0] * monthly_deviation[11])


    for i in range(0, 11):
        count = 0
        for j in range(i , len(discharge), 12):

            correlation[i+1] +=((discharge[j] - month_mean[i]) * (discharge[j +1] - month_mean[i+1]))
            #correlation[i + 1] += ((discharge[j] - month_mean[i])*(discharge[j+1] - month_mean[i+1]))/((monthly_deviation[i])*(monthly_deviation[i+1]))
            count += 1

        correlation[i+1] = correlation[i+1]/ count
        correlation[i+1] = correlation[i+1]/ (monthly_deviation[i]*monthly_deviation[i+1])

    return correlation

#print(correlation_coefficient(discharge,monthly_mean(discharge),standard_deviation(discharge,monthly_mean(discharge))))

###############################################################################################
def regression_coefficient(correlation, deviation):
    b = [0] * 12

    b[0] = correlation[0] * deviation[0]/deviation[11]
    for i in range(11):
        b[i+1] += correlation[i+1]* deviation[i+1]/deviation[i]

    return b

###################################################################################################
p = correlation_coefficient(discharge,monthly_mean(discharge),standard_deviation(discharge,monthly_mean(discharge)))
q = standard_deviation(discharge,monthly_mean(discharge))
r = monthly_mean(discharge)
s = regression_coefficient(p,q)
#print(regression_coefficient(p,q))

#print(random.normalvariate(0,1))

def synthetic_data(r,s,q,p, discharge, n):

    previous_data = discharge[len(discharge) - 12: len(discharge)]
    #print(previous_data)
    data = [0]*n
    for i in range(n):
        x = i % 12
        data[i] = r[x]+ s[x]*(previous_data[x-1]- r[x-1])+ random.normalvariate(0,1)*q[x]* math.sqrt(1- p[x]*p[x])
        previous_data[x] = data[i]

    return data


n = int(input("Enter no. of data points: "))
print(synthetic_data(r,s,q,p, discharge, n))
w = synthetic_data(r,s,q,p, discharge, n)
k = statistics.mean(w)
l = statistics.stdev(w,k)
print(f"""
Mean: {k}
Standard Deviation: {l}""")