user_study/process_data.py at master · hyperpro/user_study · 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
import math
import os

import numpy as np
import matplotlib.pyplot as plt
# from scipy import optimize


def f_log(x,A,B,C):
    return A - B*np.log(x + C)

def f_exp(x,A,B,C,D):
    return A * np.exp(B * x) + C * np.exp(D * x)

def check_length(l, name):
    flag = 0
    while(len(l) < 14):
        l.append(777)
        flag = 1
    if(flag):
        print("Warning: id- ", name, "has less than 14 samples.")
    return

def process_user(f):
    grade_str = f.readline().strip('\n').split(",")
    video_order_str = f.readline().strip('\n').split(",")
    video_time_str = f.readline().strip('\n').split(",")
    decide_time_str = f.readline().strip('\n').split(",")
    mturkID = f.readline().strip('\n')
    device = f.readline().strip('\n')
    age = f.readline().strip('\n')
    network = f.readline().strip('\n')

    check_length(grade_str, mturkID)
    check_length(video_time_str, mturkID)
    check_length(decide_time_str, mturkID)

    grade =[]
    video_order =[]
    video_time = []
    decide_time=[]
    for i in range(len(grade_str)):
        grade.append(int(grade_str[i]))
        video_order.append(int(video_order_str[i]))
        video_time.append(int(video_time_str[i]))
        decide_time.append(int(decide_time_str[i]))
    result=[grade, video_order, video_time, decide_time, mturkID, device, age, network]
    return result


fileroot = './results'
results=[]
list = os.listdir(fileroot)
print len(list) ," files detected."
for i in range(0, len(list)):
    path = os.path.join(fileroot, list[i])
    if os.path.isfile(path):
        f = open(path, 'r')
        result = process_user(f)
        results.append(result)

def gather_data():
    gather_list =[]
    for i in range(len(results)):
        gather_list.append(results[i][0])
    data = np.array(gather_list)
    print(np.shape(data))
    return data

def save_order():
    order_list = []
    for i in range(len(results)):
        order_list.append(results[i][1])
    order = np.array(order_list)
    print np.shape(order)
    np.save("ms_order.npy", order)
    return order

def look_at_time(order):
    time_list =[]
    for i in range(len(results)):
        time_list.append(results[i][2])
    time = np.array(time_list)
    unordered_time_list =[]
    for i in range(len(results)):
        temp =[]
        for j in range(13):
            temp.append(time[i][order[i][j] - 1])
        unordered_time_list.append(temp)
    unordered_time = np.array(unordered_time_list)
    return np.mean(unordered_time, axis=0), np.mean(time, axis=0)


data =gather_data()
# data[:,[8,9]] = data[:,[9,8]]
# order = save_order()
np.save("./data/ms.npy", data)
# data_mean = np.mean(data, axis=0)

# # unordered, time = look_at_time(order)


# # print(data_mean)


# x_list =[0, 50, 100, 200, 300, 500, 750, 1000, 1250, 1500, 2000, 3000]
# x = np.array(x_list)
# x1 = x
# x2 = x
# A1, B1, C1 = optimize.curve_fit(f_log, x1, data_mean)[0]
# #A2, B2, C2, D2 =optimize.curve_fit(f_exp, x2, data_mean)[0]

# data_log = f_log(x1, A1, B1, C1)
# #data_exp = f_exp(x2, 1.699, -0.002706, 3.259, -0.0003815)


# plt.figure()
# plt.scatter(x[:], data_mean[:], 15,"red")
# plt.plot(x1, data_log, "blue")
# #plt.plot(x2, data_exp, "green")
# plt.show()