-
Notifications
You must be signed in to change notification settings - Fork 0
/
acf_distinct_histogram.py
174 lines (155 loc) · 6.03 KB
/
acf_distinct_histogram.py
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
from FlokAlgorithmLocal import FlokAlgorithmLocal, FlokDataFrame
import numpy as np
import pandas as pd
import time
from datetime import datetime
class SelectTimeseries(FlokAlgorithmLocal):
def run(self, inputDataSets, params):
input_data = inputDataSets.get(0)
timeseries = params.get("timeseries", None)
if timeseries:
timeseries_list = timeseries.split(',')
output_data = input_data[timeseries_list]
else:
output_data = input_data
#print(type(output_data))
result = FlokDataFrame()
result.addDF(output_data)
return result
def run_acf(self, inputDataSets, params,time_):
input_data = inputDataSets.get(0)
#print(input_data['root.test.d2.s2'][0])
timeseries = params.get("timeseries", None)
#print(params.values())
count = 0
if timeseries:
timeseries_list = timeseries.split(',')
output_data = input_data[timeseries_list]
column = timeseries_list[1]
for i in range(len(output_data)):
if (datetime.strptime(output_data.Time[i], '%Y-%m-%d %H:%M:%S')
<= datetime.strptime(time_, '%Y-%m-%d %H:%M:%S')):
count += 1
else:
output_data = input_data
output_data.fillna(0, inplace=True)
a = output_data[column][0:count]
xcorr = np.correlate(a, a, mode='full')/output_data[column].values[count-1]
Time = []
for i in range(1, 2*count):
if i < 10:
q = time_[0:-1]+str(i)
Time.append(q)
if i >= 10:
q = time_[0:-2]+str(i)
Time.append(q)
j='acf('+column+')'
data = {'Time': Time, j: xcorr}
output_data = pd.DataFrame(data)
#print(output_data)
result = FlokDataFrame()
result.addDF(output_data)
return result
def run_distinct(self, inputDataSets, params):
input_data = inputDataSets.get(0)
timeseries = params.get("timeseries", None)
if timeseries:
timeseries_list = timeseries.split(',')
output_data = input_data[timeseries_list]
column = timeseries_list[1]
else:
output_data = input_data
# print(type(output_data))
q = len(set(output_data[column]))
j='dictinct('+column+')'
data = {'Time': (output_data['Time'][0:q]), j: list(
set(output_data[column]))}
output_data = pd.DataFrame(data)
result = FlokDataFrame()
result.addDF(output_data)
return result
def run_histogram(self, inputDataSets, params, min=0, max=0, count=1):
input_data = inputDataSets.get(0)
timeseries = params.get("timeseries", None)
if timeseries:
timeseries_list = timeseries.split(',')
output_data = input_data[timeseries_list]
column = timeseries_list[1]
else:
output_data = input_data
# print(type(output_data))
max_value=np.max(output_data[column])
if min:
pass
else:
min = -max_value
if max:
pass
else:
max = max_value
bucket = [0]*count
Time = []
# print(len(output_data['root.test.d2.s2']))
for j in range(len(output_data[column])):
if output_data[column][j] < min:
bucket[0] += 1
elif output_data[column][j] >= max:
# print(output_data['root.test.d2.s2'][j])
bucket[-1] += 1
else:
for i in range(1, count+1):
if (output_data[column][j] >= min+(i-1)*(max-min)/count
and output_data[column][j] < min+i*(max-min)/count):
bucket[i-1] += 1
for i in range(0, count):
Time.append(output_data['Time'][i])
z='histogram('+column+',min='+str(min)+',max='+str(max)+',count='+str(count)+')'
data = {'Time': Time, z: bucket}
output_data = pd.DataFrame(data)
result = FlokDataFrame()
result.addDF(output_data)
return result
if __name__ == "__main__":
algorithm = SelectTimeseries()
all_info_1 = {
"input": ["./test_in.csv"],
"inputFormat": ["csv"],
"inputLocation": ["local_fs"],
"output": ["./test_out_1.csv"],
"outputFormat": ["csv"],
"outputLocation": ["local_fs"],
"parameters": {}
}
params = all_info_1["parameters"]
inputPaths = all_info_1["input"]
inputTypes = all_info_1["inputFormat"]
inputLocation = all_info_1["inputLocation"]
outputPaths = all_info_1["output"]
outputTypes = all_info_1["outputFormat"]
outputLocation = all_info_1["outputLocation"]
dataSet = algorithm.read(inputPaths, inputTypes,
inputLocation, outputPaths, outputTypes)
result = algorithm.run(dataSet, params)
algorithm.write(outputPaths, result, outputTypes, outputLocation)
all_info_2 = {
"input": ["./test_in.csv"],
"inputFormat": ["csv"],
"inputLocation": ["local_fs"],
"output": ["./test_out_2.csv"],
"outputFormat": ["csv"],
"outputLocation": ["local_fs"],
"parameters": {"timeseries": "Time,root.test.d2.s2"}
}
params = all_info_2["parameters"]
inputPaths = all_info_2["input"]
inputTypes = all_info_2["inputFormat"]
inputLocation = all_info_2["inputLocation"]
outputPaths = all_info_2["output"]
outputTypes = all_info_2["outputFormat"]
outputLocation = all_info_2["outputLocation"]
dataSet = algorithm.read(inputPaths, inputTypes,
inputLocation, outputPaths, outputTypes)
#result = algorithm.run_acf(dataSet, params,'2022-01-01 00:00:05')
#result = algorithm.run_distinct(dataSet, params)
result = algorithm.run_histogram(dataSet, params,count=10)
algorithm.write(outputPaths, result, outputTypes, outputLocation)