Spaces:
Sleeping
Sleeping
Update src/bin/function_predictor.py
Browse files
src/bin/function_predictor.py
CHANGED
@@ -86,14 +86,11 @@ def MultiLabelSVC_cross_val_predict(representation_name, dataset, X, y, classifi
|
|
86 |
means = list(np.mean([acc_cv, f1_mi_cv, f1_ma_cv, f1_we_cv, pr_mi_cv, pr_ma_cv, pr_we_cv, rc_mi_cv, rc_ma_cv, rc_we_cv, hamm_cv], axis=1))
|
87 |
means = [np.round(i, decimals=5) for i in means]
|
88 |
|
89 |
-
stds = list(np.std([acc_cv, f1_mi_cv, f1_ma_cv, f1_we_cv, pr_mi_cv, pr_ma_cv, pr_we_cv, rc_mi_cv, rc_ma_cv, rc_we_cv, hamm_cv], axis=1))
|
90 |
-
stds = [np.round(i, decimals=5) for i in stds]
|
91 |
|
92 |
return {
|
93 |
-
"cv_results": [representation_name + "_" + dataset, acc_cv, f1_mi_cv, f1_ma_cv, f1_we_cv, pr_mi_cv, pr_ma_cv, pr_we_cv, rc_mi_cv, rc_ma_cv, rc_we_cv, hamm_cv],
|
94 |
"means": [representation_name + "_" + dataset] + means,
|
95 |
-
"stds": [representation_name + "_" + dataset] + stds,
|
96 |
-
"predictions": y_pred
|
97 |
}
|
98 |
|
99 |
def ProtDescModel():
|
@@ -108,9 +105,9 @@ def ProtDescModel():
|
|
108 |
else:
|
109 |
filtered_datasets = [dataset for dataset in datasets if aspect_type in dataset and dataset_type in dataset]
|
110 |
|
111 |
-
cv_results = []
|
112 |
cv_mean_results = []
|
113 |
-
cv_std_results = []
|
114 |
|
115 |
for dt in tqdm(filtered_datasets, total=len(filtered_datasets)):
|
116 |
print(f"Protein function prediction is started for the dataset: {dt.split('.')[0]}")
|
@@ -128,28 +125,16 @@ def ProtDescModel():
|
|
128 |
classifier=BinaryRelevance(SGDClassifier(n_jobs=cpu_number, random_state=42)))
|
129 |
|
130 |
if model is not None:
|
131 |
-
cv_results.append(model["cv_results"])
|
132 |
cv_mean_results.append(model["means"])
|
133 |
-
cv_std_results.append(model["stds"])
|
134 |
|
135 |
-
return
|
136 |
-
"cv_results": cv_results,
|
137 |
-
"cv_mean_results": cv_mean_results,
|
138 |
-
"cv_std_results": cv_std_results
|
139 |
-
}
|
140 |
|
141 |
def pred_output():
|
142 |
-
|
143 |
-
cv_result = model["cv_results"]
|
144 |
-
|
145 |
-
cv_mean_result = model["cv_mean_results"]
|
146 |
-
cv_std_result = model["cv_std_results"]
|
147 |
|
148 |
-
return
|
149 |
-
"cv_result": cv_result,
|
150 |
-
"cv_mean_result": cv_mean_result,
|
151 |
-
"cv_std_result": cv_std_result
|
152 |
-
}
|
153 |
|
154 |
# Example call to the function
|
155 |
# result = pred_output()
|
|
|
86 |
means = list(np.mean([acc_cv, f1_mi_cv, f1_ma_cv, f1_we_cv, pr_mi_cv, pr_ma_cv, pr_we_cv, rc_mi_cv, rc_ma_cv, rc_we_cv, hamm_cv], axis=1))
|
87 |
means = [np.round(i, decimals=5) for i in means]
|
88 |
|
89 |
+
#stds = list(np.std([acc_cv, f1_mi_cv, f1_ma_cv, f1_we_cv, pr_mi_cv, pr_ma_cv, pr_we_cv, rc_mi_cv, rc_ma_cv, rc_we_cv, hamm_cv], axis=1))
|
90 |
+
#stds = [np.round(i, decimals=5) for i in stds]
|
91 |
|
92 |
return {
|
|
|
93 |
"means": [representation_name + "_" + dataset] + means,
|
|
|
|
|
94 |
}
|
95 |
|
96 |
def ProtDescModel():
|
|
|
105 |
else:
|
106 |
filtered_datasets = [dataset for dataset in datasets if aspect_type in dataset and dataset_type in dataset]
|
107 |
|
108 |
+
#cv_results = []
|
109 |
cv_mean_results = []
|
110 |
+
#cv_std_results = []
|
111 |
|
112 |
for dt in tqdm(filtered_datasets, total=len(filtered_datasets)):
|
113 |
print(f"Protein function prediction is started for the dataset: {dt.split('.')[0]}")
|
|
|
125 |
classifier=BinaryRelevance(SGDClassifier(n_jobs=cpu_number, random_state=42)))
|
126 |
|
127 |
if model is not None:
|
128 |
+
#cv_results.append(model["cv_results"])
|
129 |
cv_mean_results.append(model["means"])
|
130 |
+
#cv_std_results.append(model["stds"])
|
131 |
|
132 |
+
return cv_mean_results
|
|
|
|
|
|
|
|
|
133 |
|
134 |
def pred_output():
|
135 |
+
result = ProtDescModel()
|
|
|
|
|
|
|
|
|
136 |
|
137 |
+
return result
|
|
|
|
|
|
|
|
|
138 |
|
139 |
# Example call to the function
|
140 |
# result = pred_output()
|