Skip to content
Snippets Groups Projects
Commit 61d55de4 authored by William Monroe's avatar William Monroe
Browse files

stripping notebook content

parent c7f21bd8
No related branches found
No related tags found
No related merge requests found
[core] [core]
attributesfile = ~/.gitattributes_global attributesfile = ~/.gitattributes
[filter "nbstrip_full"] [filter "nbstrip_full"]
clean = "jq --indent 1 \ clean = "jq --indent 1 \
'(.cells[] | select(has(\"outputs\")) | .outputs) = [] \ '(.cells[] | select(has(\"outputs\")) | .outputs) = [] \
...@@ -8,4 +8,4 @@ clean = "jq --indent 1 \ ...@@ -8,4 +8,4 @@ clean = "jq --indent 1 \
| .cells[].metadata = {} \ | .cells[].metadata = {} \
'" '"
smudge = cat smudge = cat
required = true required = true
\ No newline at end of file
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
import numpy as np import numpy as np
import pandas as pd import pandas as pd
import pandas_profiling import pandas_profiling
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
df = pd.read_csv('userusage.txt',delimiter='|') df = pd.read_csv('userusage.txt',delimiter='|')
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
df.head() df.head()
``` ```
%% Output %% Output
User Start JobID JobName State \ User Start JobID JobName State \
0 user 2019-01-06T22:00:21 2040834 _interactive COMPLETED 0 user 2019-01-06T22:00:21 2040834 _interactive COMPLETED
1 NaN 2019-01-06T22:00:21 2040834.batch batch COMPLETED 1 NaN 2019-01-06T22:00:21 2040834.batch batch COMPLETED
2 user 2019-01-07T16:15:21 2043373 Pipe_trim_galore COMPLETED 2 user 2019-01-07T16:15:21 2043373 Pipe_trim_galore COMPLETED
3 NaN 2019-01-07T16:15:21 2043373.batch batch COMPLETED 3 NaN 2019-01-07T16:15:21 2043373.batch batch COMPLETED
4 user 2019-01-07T16:15:21 2043374 Pipe_trim_galore COMPLETED 4 user 2019-01-07T16:15:21 2043374 Pipe_trim_galore COMPLETED
Partition MaxRSS ReqMem ReqCPUS NodeList NNodes Elapsed Partition MaxRSS ReqMem ReqCPUS NodeList NNodes Elapsed
0 medium NaN 10000Mc 1 c0088 1 16:04:23 0 medium NaN 10000Mc 1 c0088 1 16:04:23
1 NaN 1394528K 10000Mc 1 c0088 1 16:04:23 1 NaN 1394528K 10000Mc 1 c0088 1 16:04:23
2 medium NaN 2000Mc 1 c0038 1 00:18:41 2 medium NaN 2000Mc 1 c0038 1 00:18:41
3 NaN 58592K 2000Mc 1 c0038 1 00:18:41 3 NaN 58592K 2000Mc 1 c0038 1 00:18:41
4 medium NaN 2000Mc 1 c0063 1 00:15:48 4 medium NaN 2000Mc 1 c0063 1 00:15:48
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
df[['jid','step']] = df.JobID.str.split(".",expand=True) df[['jid','step']] = df.JobID.str.split(".",expand=True)
df.Partition.values df.Partition.values
``` ```
%% Output %% Output
array(['medium', nan, 'medium', ..., 'medium', nan, nan], dtype=object) array(['medium', nan, 'medium', ..., 'medium', nan, nan], dtype=object)
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
batchDF=df.dropna(subset=["MaxRSS"]) batchDF=df.dropna(subset=["MaxRSS"])
userDF=df.dropna(subset=["User"]) userDF=df.dropna(subset=["User"])
for jid in df.jid.unique(): for jid in df.jid.unique():
userDF['MaxRSS'][userDF['jid'] == jid]=batchDF['MaxRSS'][batchDF['jid'] == jid] userDF['MaxRSS'][userDF['jid'] == jid]=batchDF['MaxRSS'][batchDF['jid'] == jid]
#print(userDF[userDF['jid'] == jid]) #print(userDF[userDF['jid'] == jid])
userDF.head() userDF.head()
``` ```
%% Output %% Output
/home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: /home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/ipykernel_launcher.py:4: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
after removing the cwd from sys.path. after removing the cwd from sys.path.
/home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/pandas/core/generic.py:7626: SettingWithCopyWarning: /home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/pandas/core/generic.py:7626: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
self._update_inplace(new_data) self._update_inplace(new_data)
/home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2961: SettingWithCopyWarning: /home/wsmonroe/.conda/envs/wsmplayground/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2961: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
exec(code_obj, self.user_global_ns, self.user_ns) exec(code_obj, self.user_global_ns, self.user_ns)
%% Cell type:markdown id: tags:
# add more graphs here
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
``` ```
......
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
import sqlite3 import sqlite3
import slurm2sql import slurm2sql
import pandas as pd import pandas as pd
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
db = sqlite3.connect('test.db') db = sqlite3.connect('test.db')
slurm2sql.slurm2sql(db, ['-S', '2020-03-18', '-a']) slurm2sql.slurm2sql(db, ['-S', '2020-03-18', '-a'])
``` ```
%% Output %% Output
0 0
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
# For example, you can then convert to a dataframe: # For example, you can then convert to a dataframe:
df1 = pd.read_sql('SELECT * FROM slurm', db) df1 = pd.read_sql('SELECT * FROM slurm', db)
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
df1.head(5) df1.head(5)
``` ```
%% Output %% Output
JobID ArrayJobID ArrayTaskID JobStep JobIDSlurm \ JobID ArrayJobID ArrayTaskID JobStep JobIDSlurm \
0 3319116 3319116 NaN None 3319116_[43-45,47%5] 0 3319116 3319116 NaN None 3319116_[43-45,47%5]
1 3927198 3887451 30.0 None 3887451_30 1 3927198 3887451 30.0 None 3887451_30
2 3927198 3887451 30.0 batch 3887451_30.batch 2 3927198 3887451 30.0 batch 3887451_30.batch
3 3927198 3887451 30.0 extern 3887451_30.extern 3 3927198 3887451 30.0 extern 3887451_30.extern
4 3927199 3887451 31.0 None 3887451_31 4 3927199 3887451 31.0 None 3887451_31
JobName User Group Account State ... \ JobName User Group Account State ... \
0 1mUD1MPa user user user PENDING ... 0 1mUD1MPa user user user PENDING ...
1 100kCrC20MPa user user user COMPLETED ... 1 100kCrC20MPa user user user COMPLETED ...
2 batch user COMPLETED ... 2 batch user COMPLETED ...
3 extern user COMPLETED ... 3 extern user COMPLETED ...
4 100kCrC20MPa user user user COMPLETED ... 4 100kCrC20MPa user user user COMPLETED ...
MaxDiskReadNode MaxDiskReadTask MaxDiskWrite MaxDiskWriteNode \ MaxDiskReadNode MaxDiskReadTask MaxDiskWrite MaxDiskWriteNode \
0 NaN 0 NaN
1 NaN 1 NaN
2 c0088 0 1.222336e+10 c0088 2 c0088 0 1.222336e+10 c0088
3 c0088 0 0.000000e+00 c0088 3 c0088 0 0.000000e+00 c0088
4 NaN 4 NaN
MaxDiskWriteTask ReqGPUS Comment GPUMem GPUEff NGPU MaxDiskWriteTask ReqGPUS Comment GPUMem GPUEff NGPU
0 NaN None None None None 0 NaN None None None None
1 NaN None None None None 1 NaN None None None None
2 0 NaN None None None None 2 0 NaN None None None None
3 0 NaN None None None None 3 0 NaN None None None None
4 NaN None None None None 4 NaN None None None None
[5 rows x 63 columns] [5 rows x 63 columns]
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` python ``` python
print("more plots to come")
```
%% Output
more plots to come
%% Cell type:code id: tags:
``` python
``` ```
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment