def top_10_decision_path(crosses, crossname):
print('|symset|glo_l1|sel_l1|glo_l2|sel_l2|select_len|min|max|',
file=out_file)
print('|------|------|------|------|------|----------|---|---|',
file=out_file)
for each in crosses:
cross = each[crossname]
df_test = pd.concat([c.df_test for c in cross])
df_select, df_year, df_month = ana.select2(confer.score1,
confer.score2, df_test,
1, 10)
print('|%s|%.2f|%.2f|%.2f|%.2f|%d|%.2f|%.2f|' %
(each["symsetname"], ana.accurate(df_test, confer.score1),
ana.accurate(df_select, confer.score1),
ana.accurate(df_test, confer.score2),
ana.accurate(df_select, confer.score2), len(df_select),
df_select.tail(1)["pred"] if len(df_select) > 0 else 0,
df_select.head(1)["pred"] if len(df_select) > 0 else 0),
file=out_file)
np_feat = df_select[base.get_feat_names(df_select)].values
classifier = cross[0].classifier
for i in range(len(np_feat)):
x = np_feat[i, :]
print(x)
dot_file = os.path.join(
root, "data", "cross",
'top_10_decision_path-%s-%d' % (each["symsetname"], i))
decision_path.export_decision_path2(
classifier,
x,
dot_file + ".dot",
feature_names=base.get_feat_names(df_select))
import pydot
(graph, ) = pydot.graph_from_dot_file(dot_file + ".dot")
graph.write_png(dot_file + ".png")
for each in crosses:
for i in range(10):
dot_file = os.path.join(
root, "data", "cross",
'top_10_decision_path-%s-%d' % (each["symsetname"], i))
print("" % (dot_file), file=out_file)
def accurate(crosses, crossname):
print('\n\n|symset|glo_l1|sel_l1|glo_l2|sel_l2|select_len|min|max|', file=out_file)
print('|------|------|------|------|------|----------|---|---|', file=out_file)
for threshold in [2000, 1000, 500, 200, 100]:
for each in crosses:
cross = each[crossname]
df_test = pd.concat([c.df_test for c in cross])
df_test.sort_values("pred", ascending=False, inplace=True)
df_select, df_year, df_month = ana.select2( confer.score1, confer.score2,
df_test,
2, threshold)
print('|%s|%.2f|%.2f|%.2f|%.2f|%d|%.2f|%.2f|'
% (
each["symsetname"],
ana.accurate(df_test, confer.score1),
ana.accurate(df_select, confer.score1),
ana.accurate(df_test, confer.score2),
ana.accurate(df_select , confer.score2),
len(df_select),
df_select.tail(1)["pred"] if len(df_select) > 0 else 0,
df_select.head(1)["pred"] if len(df_select) > 0 else 0), file=out_file)
def accurate(crosses, crossname):
print('\n\n|symset|glo_l1|sel_l1|glo_l2|sel_l2|select_len|min|max|',
file=out_file)
print('|------|------|------|------|------|----------|---|---|',
file=out_file)
for threshold in [2000, 1000, 500, 200, 100]:
for each in crosses:
cross = each[crossname]
df_test = pd.concat([c.df_test for c in cross])
df_test.sort_values("pred", ascending=False, inplace=True)
df_select, df_year, df_month = ana.select2(
confer.score1, confer.score2, df_test, 2, threshold)
print(
'|%s|%.2f|%.2f|%.2f|%.2f|%d|%.2f|%.2f|' %
(each["symsetname"], ana.accurate(df_test, confer.score1),
ana.accurate(df_select, confer.score1),
ana.accurate(df_test, confer.score2),
ana.accurate(df_select, confer.score2), len(df_select),
df_select.tail(1)["pred"] if len(df_select) > 0 else 0,
df_select.head(1)["pred"] if len(df_select) > 0 else 0),
file=out_file)
def top_10_decision_path(crosses, crossname):
print('|symset|glo_l1|sel_l1|glo_l2|sel_l2|select_len|min|max|', file=out_file)
print('|------|------|------|------|------|----------|---|---|', file=out_file)
for each in crosses:
cross = each[crossname]
df_test = pd.concat([c.df_test for c in cross])
df_select, df_year, df_month = ana.select2(confer.score1, confer.score2, df_test,
1, 10)
print('|%s|%.2f|%.2f|%.2f|%.2f|%d|%.2f|%.2f|'
% (
each["symsetname"],
ana.accurate(df_test, confer.score1),
ana.accurate(df_select, confer.score1),
ana.accurate(df_test, confer.score2),
ana.accurate(df_select , confer.score2),
len(df_select),
df_select.tail(1)["pred"] if len(df_select) > 0 else 0,
df_select.head(1)["pred"] if len(df_select) > 0 else 0), file=out_file)
np_feat = df_select[base.get_feat_names(df_select)].values
classifier = cross[0].classifier
for i in range(len(np_feat)):
x = np_feat[i,:]
print(x)
dot_file = os.path.join(root, "data", "cross",
'top_10_decision_path-%s-%d'
% (each["symsetname"], i))
decision_path.export_decision_path2(classifier, x, dot_file + ".dot" ,
feature_names=base.get_feat_names(df_select))
import pydot
(graph,) = pydot.graph_from_dot_file(dot_file + ".dot")
graph.write_png(dot_file + ".png")
for each in crosses:
for i in range(10):
dot_file = os.path.join(root, "data", "cross",
'top_10_decision_path-%s-%d'
% (each["symsetname"], i))
print("" % (dot_file), file=out_file)
#!/usr/bin/env python2.7