Skip to content

GitLab

Unverified Commit b5c7c85d authored by Yuting Jiang's avatar Yuting Jiang Committed by GitHub
Browse files

Analyzer: Rename fields in json of data diagnosis to be more readable (#382) 

**Description**
Rename field in data diagnosis to be more readable.

**Major Revision**
- rename fields according to diagnosis/metric format

**Minor Revision**
- change type of diagnosis/issue_num to be int
parent 9c29c931
Hide whitespace changes
Inline Side-by-side
Showing with 28 additions and 17 deletions
superbench/analyzer/data_diagnosis.py
View file @ b5c7c85d
......@@ -232,20 +232,22 @@ def output_all_nodes_results(self, raw_data_df, data_not_accept_df):
data_not_accept_df (DataFrame): defective nodes's detailed information
Returns:
DataFrame: all nodes' detailed information inluding ['Accept','#Issues','Category','Issue_Details']
DataFrame: all nodes' detailed information inluding ['Accept','Number_Of_Issues','Category','Issue_Details']
"""
append_columns = ['Accept', '#Issues', 'Category', 'Issue_Details']
append_columns = ['Accept', 'Number_Of_Issues', 'Category', 'Issue_Details']
all_data_df = (raw_data_df).astype('float64')
if data_not_accept_df.shape[0] == 0:
all_data_df['Accept'] = [True for i in range(len(all_data_df))]
all_data_df['#Issues'] = [0 for i in range(len(all_data_df))]
all_data_df['Number_Of_Issues'] = [0 for i in range(len(all_data_df))]
all_data_df['Category'] = [None for i in range(len(all_data_df))]
all_data_df['Issue_Details'] = [None for i in range(len(all_data_df))]
elif data_not_accept_df.shape[0] > 0:
data_not_accept_df['Accept'] = [False for i in range(len(data_not_accept_df))]
data_not_accept_df['#Issues'] = data_not_accept_df['Defective Details'].map(lambda x: len(x.split(',')))
data_not_accept_df['Number_Of_Issues'] = data_not_accept_df['Defective Details'].map(
lambda x: len(x.split(','))
)
data_not_accept_df = data_not_accept_df.rename(columns={'Defective Details': 'Issue_Details'})
for index in range(len(append_columns)):
if append_columns[index] not in data_not_accept_df:
......@@ -260,7 +262,8 @@ def output_all_nodes_results(self, raw_data_df, data_not_accept_df):
data_not_accept_df[[append_columns[index]]], left_index=True, right_index=True, how='left'
)
all_data_df['Accept'] = all_data_df['Accept'].replace(np.nan, True)
all_data_df['#Issues'] = all_data_df['#Issues'].replace(np.nan, 0)
all_data_df['Number_Of_Issues'] = all_data_df['Number_Of_Issues'].replace(np.nan, 0)
all_data_df['Number_Of_Issues'] = all_data_df['Number_Of_Issues'].astype(int)
all_data_df = all_data_df.replace(np.nan, '')
......@@ -321,6 +324,14 @@ def output_diagnosis_in_json(self, data_not_accept_df, output_path):
output_path (str): the path of output jsonl file
"""
data_not_accept_df['Index'] = data_not_accept_df.index
data_not_accept_df = data_not_accept_df.rename(
columns={
'Issue_Details': 'diagnosis/issue_details',
'Category': 'diagnosis/category',
'Number_Of_Issues': 'diagnosis/issue_num',
'Accept': 'diagnosis/accept'
}
)
data_not_accept_json = data_not_accept_df.to_json(orient='records')
data_not_accept = json.loads(data_not_accept_json)
p = Path(output_path)
......
tests/data/diagnosis_summary.json
View file @ b5c7c85d
......@@ -462,10 +462,10 @@
"vgg_models/pytorch-vgg19/throughput_train_float32": 429.8092158311,
"vgg_models/pytorch-vgg19/steptime_train_float16": 45.2033062465,
"vgg_models/pytorch-vgg19/throughput_train_float16": 709.1127328377,
"Accept": false,
"#Issues": 1.0,
"Category": "KernelLaunch",
"Issue_Details": "kernel-launch/event_overhead:0(B/L: 0.0060 VAL: 0.1000 VAR: 1577.85% Rule:lambda x:x>0.05)",
"diagnosis/accept": false,
"diagnosis/issue_num": 1,
"diagnosis/category": "KernelLaunch",
"diagnosis/issue_details": "kernel-launch/event_overhead:0(B/L: 0.0060 VAL: 0.1000 VAR: 1577.85% Rule:lambda x:x>0.05)",
"Index": "sb-validation-01"
},
{
......@@ -931,10 +931,10 @@
"vgg_models/pytorch-vgg19/throughput_train_float32": 429.8092158311,
"vgg_models/pytorch-vgg19/steptime_train_float16": 45.2033062465,
"vgg_models/pytorch-vgg19/throughput_train_float16": 709.1127328377,
"Accept": true,
"#Issues": 0.0,
"Category": "",
"Issue_Details": "",
"diagnosis/accept": true,
"diagnosis/issue_num": 0,
"diagnosis/category": "",
"diagnosis/issue_details": "",
"Index": "sb-validation-02"
},
{
......@@ -1400,10 +1400,10 @@
"vgg_models/pytorch-vgg19/throughput_train_float32": 429.8092158311,
"vgg_models/pytorch-vgg19/steptime_train_float16": 45.2033062465,
"vgg_models/pytorch-vgg19/throughput_train_float16": 709.1127328377,
"Accept": false,
"#Issues": 17.0,
"Category": "FailedTest",
"Issue_Details": "mem-bw/D2H_Mem_BW:0_miss,mem-bw/D2H_Mem_BW:1_miss,mem-bw/D2H_Mem_BW:2_miss,mem-bw/D2H_Mem_BW:3_miss,mem-bw/D2H_Mem_BW:4_miss,mem-bw/D2H_Mem_BW:5_miss,mem-bw/D2H_Mem_BW:6_miss,mem-bw/D2H_Mem_BW:7_miss,mem-bw/H2D_Mem_BW:0_miss,mem-bw/H2D_Mem_BW:1_miss,mem-bw/H2D_Mem_BW:2_miss,mem-bw/H2D_Mem_BW:3_miss,mem-bw/H2D_Mem_BW:4_miss,mem-bw/H2D_Mem_BW:5_miss,mem-bw/H2D_Mem_BW:6_miss,mem-bw/H2D_Mem_BW:7_miss,mem-bw/return_code(VAL: 1.0000 Rule:lambda x:x>0)",
"diagnosis/accept": false,
"diagnosis/issue_num": 17,
"diagnosis/category": "FailedTest",
"diagnosis/issue_details": "mem-bw/D2H_Mem_BW:0_miss,mem-bw/D2H_Mem_BW:1_miss,mem-bw/D2H_Mem_BW:2_miss,mem-bw/D2H_Mem_BW:3_miss,mem-bw/D2H_Mem_BW:4_miss,mem-bw/D2H_Mem_BW:5_miss,mem-bw/D2H_Mem_BW:6_miss,mem-bw/D2H_Mem_BW:7_miss,mem-bw/H2D_Mem_BW:0_miss,mem-bw/H2D_Mem_BW:1_miss,mem-bw/H2D_Mem_BW:2_miss,mem-bw/H2D_Mem_BW:3_miss,mem-bw/H2D_Mem_BW:4_miss,mem-bw/H2D_Mem_BW:5_miss,mem-bw/H2D_Mem_BW:6_miss,mem-bw/H2D_Mem_BW:7_miss,mem-bw/return_code(VAL: 1.0000 Rule:lambda x:x>0)",
"Index": "sb-validation-03"
}
]
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment