bit_stomach_python/trend_annotate.py at main · Display-Lab/bit_stomach_python · 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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152

from scipy import stats
import pandas as pd
from rdflib import Literal, URIRef, BNode
from rdflib.namespace import RDF

#from calc_gaps_slopes import gap_calc,trend_calc,monotonic_pred,mod_collector

s=URIRef("http://example.com/app#display-lab")
p=URIRef('http://example.com/slowmo#IsAboutMeasure')


def trend_annotate(input_graph,s13,latest_measure_df,comparator_bnode):
    back_up_df=latest_measure_df
    s14=s13
    p14=URIRef('http://purl.obolibrary.org/obo/RO_0000091')
    latest_measure_df=latest_measure_df.reset_index(drop=True)
    idx= latest_measure_df.groupby(['measure'])['month'].nlargest(2) .reset_index()
    l=idx['level_1'].tolist()
    latest_measure_df =  latest_measure_df[latest_measure_df.index.isin(l)]
    latest_measure_df = latest_measure_df.reset_index(drop=True)
    trend_sign=latest_measure_df["Performance_Rate"][1]-latest_measure_df["Performance_Rate"][0]
    #back_up_df.to_csv('slope22.csv')
    #print(trend_sign)
    if trend_sign<0:
        ac=BNode(latest_measure_df["measure"][0])
        av=comparator_bnode

    #         #annotate goal comparator
        o14=BNode()
        input_graph.add((s14,p14,o14))
        #input_graph=annotate_goal_negative_trend(input_graph,o14,ac,av)
        trend_sign1="negative"
        number=find_number(back_up_df,trend_sign1)
        idx= back_up_df.groupby(['measure'])['month'].nlargest(number) .reset_index()
        l=idx['level_1'].tolist()
        measure_df =  back_up_df[back_up_df.index.isin(l)]
        out = latest_measure_df.groupby('measure').apply(theil_reg, xcol='month', ycol='Performance_Rate')
        df_1=out[0]
        df_1 = df_1.reset_index()
        df_1 = df_1.rename({0:"performance_trend_slope"}, axis=1)

        trend_slope=df_1["performance_trend_slope"][0]

        # print(trend_slope)
        # print(number)
        input_graph=annotate_negative_trend(input_graph,o14,ac,av,trend_slope,number)

    if trend_sign>0:
        ac=BNode(latest_measure_df["measure"][0])
        av=comparator_bnode

    #         #annotate goal comparator
        o14=BNode()
        input_graph.add((s14,p14,o14))
        trend_sign1="positive"
        number=find_number(back_up_df,trend_sign1)
        idx= back_up_df.groupby(['measure'])['month'].nlargest(number) .reset_index()
        l=idx['level_1'].tolist()
        measure_df =  back_up_df[back_up_df.index.isin(l)]
        out = latest_measure_df.groupby('measure').apply(theil_reg, xcol='month', ycol='Performance_Rate')
        df_1=out[0]
        df_1 = df_1.reset_index()
        df_1 = df_1.rename({0:"performance_trend_slope"}, axis=1)

        trend_slope=df_1["performance_trend_slope"][0]
        input_graph=annotate_positive_trend(input_graph,o14,ac,av,trend_slope,number)

    #a=insert_annotate(input_graph)


    return input_graph

def annotate_negative_trend(a,s16,measure_Name,o16,trend_slope,number):
    p15=RDF.type
    o15=URIRef('http://purl.obolibrary.org/obo/PSDO_0000100')
    a.add((s16,p15,o15))
    p16=URIRef('http://example.com/slowmo#RegardingComparator')
    a.add((s16,p16,o16))
    p17=URIRef('http://example.com/slowmo#RegardingMeasure')
    o17=measure_Name
    a.add((s16,p17,o17))
    trend_slope=Literal(trend_slope)
    number=Literal(number)
    p18=URIRef('http://example.com/slowmo#PerformanceTrendSlope')
    o18=trend_slope
    a.add((s16,p18,o18))
    p18=URIRef('http://example.com/slowmo#numberofmonths')
    o18=number
    a.add((s16,p18,o18))
    return a

def annotate_positive_trend(a,s16,measure_Name,o16,trend_slope,number):
    p15=RDF.type
    o15=URIRef('http://purl.obolibrary.org/obo/PSDO_0000099')
    a.add((s16,p15,o15))
    p16=URIRef('http://example.com/slowmo#RegardingComparator')
    a.add((s16,p16,o16))
    p17=URIRef('http://example.com/slowmo#RegardingMeasure')
    o17=measure_Name
    a.add((s16,p17,o17))
    trend_slope=Literal(trend_slope)
    number=Literal(number)
    p18=URIRef('http://example.com/slowmo#PerformanceTrendSlope')
    o18=trend_slope
    a.add((s16,p18,o18))
    p18=URIRef('http://example.com/slowmo#numberofmonths')
    o18=number
    a.add((s16,p18,o18))
    return a


def find_number(backup_df,trend_sign1):
    if(trend_sign1=="negative"):
        x=2
        lista=[]
        lista=backup_df["Performance_Rate"].tolist()
        count=0
        y=-1
        z=y-1
        for x in range(len(lista)):
            if lista[z]<=lista[y]:
                return count
            if(lista[z]>lista[y]):
                count=count+1
                y=y-1
                z=y-1
        return count
    if(trend_sign1=="positive"):
        x=2
        lista=[]
        lista=backup_df["Performance_Rate"].tolist()
        count=0
        y=-1
        z=y-1
        for x in range(len(lista)):
            if lista[z]>=lista[y]:
                return count
            if(lista[z]<lista[y]):
                count=count+1
                y=y-1
                z=y-1
        return count

def theil_reg(df, xcol, ycol):

   model = stats.theilslopes(df[ycol],df[xcol])
   return pd.Series(model)