griffithlab/pVACtools | Build 19267929486 | pvactools/lib/sort.py | Coveralls

1

import pandas as pd

3✔

2

from pvactools.lib.run_utils import *

3✔

4

def pvacseq_sort(rows, top_score_metric, top_score_metric2, file_type='full'):

3✔

5

    if isinstance(rows, list):

3✔

6

        rows = pd.DataFrame.from_dict(rows)

3✔

7

    if len(rows) == 0:

3✔

8

        return rows

3✔

10

    if file_type == 'aggregated':

3✔

11

        tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "PoorTranscript", "LowExpr", "Anchor", "Subclonal", "ProbPos", "Poor", "NoExpr"]

3✔

12

        sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))

3✔

13

        rows["rank_tier"] = rows['Tier'].map(sorter_index)

3✔

14

        sort_columns = ["rank_tier", "rank", "Gene", "AA Change"]

3✔

15

        expression_column = 'Allele Expr'

3✔

16

    elif file_type == 'full':

3✔

17

        sort_columns = ["rank", "Gene Name", "Mutation"]

3✔

18

        expression_column = 'Gene Expression'

3✔

20

    rows["rank_expr"] = pd.to_numeric(rows[expression_column], errors='coerce').rank(ascending=False, method='dense', na_option="bottom")

3✔

21

    rows["rank"] = rows["rank_expr"]

3✔

23

    if file_type == 'aggregated':

3✔

24

        for metric2 in top_score_metric2:

3✔

25

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

26

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

27

    elif file_type == 'full':

3✔

28

        for metric2 in top_score_metric2:

3✔

29

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacseq', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

30

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

32

    rows.sort_values(by=sort_columns, inplace=True, ascending=True)

3✔

34

    rows.drop(labels='rank', axis=1, inplace=True)

3✔

35

    if file_type == 'aggregated':

3✔

36

        rows.drop(labels='rank_tier', axis=1, inplace=True)

3✔

37

    rows.drop(labels='rank_expr', axis=1, inplace=True)

3✔

38

    for metric2 in top_score_metric2:

3✔

39

        rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)

3✔

41

    return rows

3✔

43

def pvacfuse_sort(rows, top_score_metric, top_score_metric2, file_type='full'):

3✔

44

    if isinstance(rows, list):

3✔

45

        rows = pd.DataFrame.from_dict(rows)

3✔

46

    if len(rows) == 0:

3✔

49

    if file_type == 'aggregated':

3✔

50

        tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "LowReadSupport", "LowExpr", "ProbPos", "Poor"]

3✔

51

        sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))

3✔

52

        rows["rank_tier"] = rows['Tier'].map(sorter_index)

3✔

53

        sort_columns = ["rank_tier", "rank", "ID"]

3✔

54

        expression_column = 'Expr'

3✔

55

    elif file_type == 'full':

3✔

56

        sort_columns = ["rank", "Mutation"]

3✔

57

        expression_column = 'Expression'

3✔

59

    rows["rank_expr"] = pd.to_numeric(rows[expression_column], errors='coerce').rank(ascending=False, method='dense', na_option="bottom")

3✔

60

    rows["rank"] = rows["rank_expr"]

3✔

62

    if file_type == 'aggregated':

3✔

63

        for metric2 in top_score_metric2:

3✔

64

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

65

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

66

    elif file_type == 'full':

3✔

67

        for metric2 in top_score_metric2:

3✔

68

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacfuse', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

69

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

71

    rows.sort_values(by=sort_columns, inplace=True, ascending=True)

3✔

73

    rows.drop(labels='rank', axis=1, inplace=True)

3✔

74

    if file_type == 'aggregated':

3✔

75

        rows.drop(labels='rank_tier', axis=1, inplace=True)

3✔

76

    rows.drop(labels='rank_expr', axis=1, inplace=True)

3✔

77

    for metric2 in top_score_metric2:

3✔

78

        rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)

3✔

80

    return rows

3✔

82

def pvacsplice_sort(rows, top_score_metric, top_score_metric2, file_type='full'):

3✔

83

    if isinstance(rows, list):

3✔

84

        rows = pd.DataFrame.from_dict(rows)

3✔

85

    if len(rows) == 0:

3✔

86

        return rows

3✔

88

    if file_type == 'aggregated':

3✔

89

        tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "PoorTranscript", "LowExpr", "Subclonal", "ProbPos", "Poor", "NoExpr"]

3✔

90

        sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))

3✔

91

        rows["rank_tier"] = rows['Tier'].map(sorter_index)

3✔

92

        sort_columns = ["rank_tier", "rank", "Gene", "Transcript", "AA Change"]

3✔

93

        expression_column = 'Allele Expr'

3✔

94

    elif file_type == 'full':

3✔

95

        sort_columns = ["rank", "Gene Name", "Transcript", "Amino Acid Change"]

3✔

96

        expression_column = 'Gene Expression'

3✔

98

    rows["rank_expr"] = pd.to_numeric(rows[expression_column], errors='coerce').rank(ascending=False, method='dense', na_option="bottom")

3✔

99

    rows["rank"] = rows["rank_expr"]

3✔

101

    if file_type == 'aggregated':

3✔

102

        for metric2 in top_score_metric2:

3✔

103

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

104

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

105

    elif file_type == 'full':

3✔

106

        for metric2 in top_score_metric2:

3✔

107

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacsplice', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

108

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

110

    rows.sort_values(by=sort_columns, inplace=True, ascending=True)

3✔

112

    rows.drop(labels='rank', axis=1, inplace=True)

3✔

113

    if file_type == 'aggregated':

3✔

114

        rows.drop(labels='rank_tier', axis=1, inplace=True)

3✔

115

    rows.drop(labels='rank_expr', axis=1, inplace=True)

3✔

116

    for metric2 in top_score_metric2:

3✔

117

        rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)

3✔

119

    return rows

3✔

121

def pvacbind_sort(rows, top_score_metric, top_score_metric2, file_type='full'):

3✔

122

    if isinstance(rows, list):

3✔

123

        rows = pd.DataFrame.from_dict(rows)

3✔

124

    if len(rows) == 0:

3✔

127

    if file_type == 'aggregated':

3✔

128

        tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "ProbPos", "Poor"]

3✔

129

        sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))

3✔

130

        rows["rank_tier"] = rows['Tier'].map(sorter_index)

3✔

131

        sort_columns = ["rank_tier", "rank", "ID"]

3✔

132

    elif file_type == 'full':

3✔

133

        sort_columns = ["rank", "Mutation"]

3✔

135

    rows["rank"] = 0

3✔

136

    if file_type == 'aggregated':

3✔

137

        for metric2 in top_score_metric2:

3✔

138

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

139

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

140

    elif file_type == 'full':

3✔

141

        for metric2 in top_score_metric2:

3✔

142

            rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacbind', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')

3✔

143

            rows["rank"] += rows[f"rank_{metric2}"]

3✔

145

    rows.sort_values(by=sort_columns, inplace=True, ascending=True)

3✔

147

    rows.drop(labels='rank', axis=1, inplace=True)

3✔

148

    if file_type == 'aggregated':

3✔

149

        rows.drop(labels='rank_tier', axis=1, inplace=True)

3✔

150

    for metric2 in top_score_metric2:

3✔

151

        rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)

3✔

153

    return rows

3✔

griffithlab / pVACtools / 19267929486

Source File
Press 'n' to go to next uncovered line, 'b' for previous

1	import pandas as pd	3✔
2	from pvactools.lib.run_utils import *	3✔
3
4	def pvacseq_sort(rows, top_score_metric, top_score_metric2, file_type='full'):	3✔
5	if isinstance(rows, list):	3✔
6	rows = pd.DataFrame.from_dict(rows)	3✔
7	if len(rows) == 0:	3✔
8	return rows	3✔
9
10	if file_type == 'aggregated':	3✔
11	tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "PoorTranscript", "LowExpr", "Anchor", "Subclonal", "ProbPos", "Poor", "NoExpr"]	3✔
12	sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))	3✔
13	rows["rank_tier"] = rows['Tier'].map(sorter_index)	3✔
14	sort_columns = ["rank_tier", "rank", "Gene", "AA Change"]	3✔
15	expression_column = 'Allele Expr'	3✔
16	elif file_type == 'full':	3✔
17	sort_columns = ["rank", "Gene Name", "Mutation"]	3✔
18	expression_column = 'Gene Expression'	3✔
19
20	rows["rank_expr"] = pd.to_numeric(rows[expression_column], errors='coerce').rank(ascending=False, method='dense', na_option="bottom")	3✔
21	rows["rank"] = rows["rank_expr"]	3✔
22
23	if file_type == 'aggregated':	3✔
24	for metric2 in top_score_metric2:	3✔
25	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
26	rows["rank"] += rows[f"rank_{metric2}"]	3✔
27	elif file_type == 'full':	3✔
28	for metric2 in top_score_metric2:	3✔
29	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacseq', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
30	rows["rank"] += rows[f"rank_{metric2}"]	3✔
31
32	rows.sort_values(by=sort_columns, inplace=True, ascending=True)	3✔
33
34	rows.drop(labels='rank', axis=1, inplace=True)	3✔
35	if file_type == 'aggregated':	3✔
36	rows.drop(labels='rank_tier', axis=1, inplace=True)	3✔
37	rows.drop(labels='rank_expr', axis=1, inplace=True)	3✔
38	for metric2 in top_score_metric2:	3✔
39	rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)	3✔
40
41	return rows	3✔
42
43	def pvacfuse_sort(rows, top_score_metric, top_score_metric2, file_type='full'):	3✔
44	if isinstance(rows, list):	3✔
45	rows = pd.DataFrame.from_dict(rows)	3✔
46	if len(rows) == 0:	3✔
NEW 47	return rows	×
48
49	if file_type == 'aggregated':	3✔
50	tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "LowReadSupport", "LowExpr", "ProbPos", "Poor"]	3✔
51	sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))	3✔
52	rows["rank_tier"] = rows['Tier'].map(sorter_index)	3✔
53	sort_columns = ["rank_tier", "rank", "ID"]	3✔
54	expression_column = 'Expr'	3✔
55	elif file_type == 'full':	3✔
56	sort_columns = ["rank", "Mutation"]	3✔
57	expression_column = 'Expression'	3✔
58
59	rows["rank_expr"] = pd.to_numeric(rows[expression_column], errors='coerce').rank(ascending=False, method='dense', na_option="bottom")	3✔
60	rows["rank"] = rows["rank_expr"]	3✔
61
62	if file_type == 'aggregated':	3✔
63	for metric2 in top_score_metric2:	3✔
64	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
65	rows["rank"] += rows[f"rank_{metric2}"]	3✔
66	elif file_type == 'full':	3✔
67	for metric2 in top_score_metric2:	3✔
68	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacfuse', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
69	rows["rank"] += rows[f"rank_{metric2}"]	3✔
70
71	rows.sort_values(by=sort_columns, inplace=True, ascending=True)	3✔
72
73	rows.drop(labels='rank', axis=1, inplace=True)	3✔
74	if file_type == 'aggregated':	3✔
75	rows.drop(labels='rank_tier', axis=1, inplace=True)	3✔
76	rows.drop(labels='rank_expr', axis=1, inplace=True)	3✔
77	for metric2 in top_score_metric2:	3✔
78	rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)	3✔
79
80	return rows	3✔
81
82	def pvacsplice_sort(rows, top_score_metric, top_score_metric2, file_type='full'):	3✔
83	if isinstance(rows, list):	3✔
84	rows = pd.DataFrame.from_dict(rows)	3✔
85	if len(rows) == 0:	3✔
86	return rows	3✔
87
88	if file_type == 'aggregated':	3✔
89	tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "PoorTranscript", "LowExpr", "Subclonal", "ProbPos", "Poor", "NoExpr"]	3✔
90	sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))	3✔
91	rows["rank_tier"] = rows['Tier'].map(sorter_index)	3✔
92	sort_columns = ["rank_tier", "rank", "Gene", "Transcript", "AA Change"]	3✔
93	expression_column = 'Allele Expr'	3✔
94	elif file_type == 'full':	3✔
95	sort_columns = ["rank", "Gene Name", "Transcript", "Amino Acid Change"]	3✔
96	expression_column = 'Gene Expression'	3✔
97
98	rows["rank_expr"] = pd.to_numeric(rows[expression_column], errors='coerce').rank(ascending=False, method='dense', na_option="bottom")	3✔
99	rows["rank"] = rows["rank_expr"]	3✔
100
101	if file_type == 'aggregated':	3✔
102	for metric2 in top_score_metric2:	3✔
103	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
104	rows["rank"] += rows[f"rank_{metric2}"]	3✔
105	elif file_type == 'full':	3✔
106	for metric2 in top_score_metric2:	3✔
107	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacsplice', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
108	rows["rank"] += rows[f"rank_{metric2}"]	3✔
109
110	rows.sort_values(by=sort_columns, inplace=True, ascending=True)	3✔
111
112	rows.drop(labels='rank', axis=1, inplace=True)	3✔
113	if file_type == 'aggregated':	3✔
114	rows.drop(labels='rank_tier', axis=1, inplace=True)	3✔
115	rows.drop(labels='rank_expr', axis=1, inplace=True)	3✔
116	for metric2 in top_score_metric2:	3✔
117	rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)	3✔
118
119	return rows	3✔
120
121	def pvacbind_sort(rows, top_score_metric, top_score_metric2, file_type='full'):	3✔
122	if isinstance(rows, list):	3✔
123	rows = pd.DataFrame.from_dict(rows)	3✔
124	if len(rows) == 0:	3✔
NEW 125	return rows	×
126
127	if file_type == 'aggregated':	3✔
128	tier_sorter = ["Pass", "PoorBinder", "PoorImmunogenicity", "PoorPresentation", "RefMatch", "ProbPos", "Poor"]	3✔
129	sorter_index = dict(zip(tier_sorter,range(len(tier_sorter))))	3✔
130	rows["rank_tier"] = rows['Tier'].map(sorter_index)	3✔
131	sort_columns = ["rank_tier", "rank", "ID"]	3✔
132	elif file_type == 'full':	3✔
133	sort_columns = ["rank", "Mutation"]	3✔
134
135	rows["rank"] = 0	3✔
136	if file_type == 'aggregated':	3✔
137	for metric2 in top_score_metric2:	3✔
138	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metric2_to_aggregate_column(metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
139	rows["rank"] += rows[f"rank_{metric2}"]	3✔
140	elif file_type == 'full':	3✔
141	for metric2 in top_score_metric2:	3✔
142	rows[f"rank_{metric2}"] = pd.to_numeric(rows[metrics_to_column('pvacbind', top_score_metric, metric2)], errors='coerce').rank(ascending=True, method='dense', na_option='bottom')	3✔
143	rows["rank"] += rows[f"rank_{metric2}"]	3✔
144
145	rows.sort_values(by=sort_columns, inplace=True, ascending=True)	3✔
146
147	rows.drop(labels='rank', axis=1, inplace=True)	3✔
148	if file_type == 'aggregated':	3✔
149	rows.drop(labels='rank_tier', axis=1, inplace=True)	3✔
150	for metric2 in top_score_metric2:	3✔
151	rows.drop(labels=f"rank_{metric2}", axis=1, inplace=True)	3✔
152
153	return rows	3✔

griffithlab / pVACtools / 19267929486

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous