[1]:

from ckg.report_manager import project
from ckg.analytics_core.analytics import analytics
from ckg.analytics_core.viz import viz

from plotly.offline import init_notebook_mode, iplot
%matplotlib inline
init_notebook_mode(connected=True)

c:\users\sande\.conda\envs\pip_rev\lib\site-packages\outdated\utils.py:18: OutdatedPackageWarning:

The package pingouin is out of date. Your version is 0.3.11, the latest is 0.3.12.
Set the environment variable OUTDATED_IGNORE=1 to disable these warnings.


WGCNA functions will not work. Module Rpy2 not installed.
R functions will not work. Module Rpy2 not installed.

[3]:

p = project.Project(identifier='P0000014')
p.build_project(force=False)
p.generate_report()

[4]:

proteomics_dataset = p.get_dataset('proteomics')
pro_processed = proteomics_dataset.get_dataframe("processed")

[5]:

pro_processed = pro_processed.drop(['sample', 'subject'], axis=1)

[6]:

pro_processed.head()

[6]:
A2M~P01023 A30~A2MYE2 ABI3BP~Q7Z7G0 ACE~P12821 ACTB~P60709 ACTN1~P12814 ADA2~Q9NZK5 ADAMTS13~Q76LX8 ADAMTSL4~Q6UY14 ADH4~P08319 ... VCL~P18206 VH6DJ~A2N0T4 VIM~P08670 VK3~A2N2F4 VNN1~O95497 VTN~P04004 VWF~P04275 YWHAZ~P63104 group scFv~Q65ZC9
0 38.005564 28.173504 21.631230 22.251041 27.090330 25.039968 23.442151 24.010605 25.085820 23.389032 ... 26.337731 31.159485 24.178889 25.835908 22.480055 32.815815 28.922779 22.347244 Cirrhosis 27.788928
1 37.309118 27.981907 27.342062 23.847270 27.461155 25.896268 23.754503 24.135818 19.400048 22.148706 ... 25.535996 31.994997 23.709777 25.004889 23.852908 32.722121 29.881279 22.141285 Cirrhosis 26.869972
2 37.384952 28.857627 21.080035 22.863630 27.929764 24.295225 23.359443 24.121788 24.923476 23.017163 ... 25.858635 30.139559 23.599064 26.271650 24.232132 32.755752 29.444625 21.972598 Cirrhosis 28.069328
3 38.417225 28.978380 25.501910 22.992774 27.152479 25.231288 23.701340 24.568309 24.878802 26.388112 ... 26.531017 31.977294 24.179076 25.929200 24.269047 32.714014 29.397176 22.216971 Cirrhosis 28.170209
4 37.471303 28.748744 20.200498 21.326143 27.537048 22.392992 22.406264 24.961173 20.480569 24.339540 ... 26.355535 30.485582 23.865224 26.701340 20.953141 32.722691 28.540895 18.630532 Cirrhosis 28.612280

5 rows × 510 columns

[7]:

sample_size, power_df = analytics.power_analysis(pro_processed, group='group', groups=None, alpha=0.05, power=0.8, dep_var='nobs', figure=True)
print('Sample Size: %.3f' % sample_size)

Sample Size: 50.400

[8]:

plot = viz.get_scatterplot(power_df, identifier='power', args={'x':'#samples',
                                                               'y':'power',
                                                               'name':'labels',
                                                               'group':'labels',
                                                               'x_title': 'Number of Samples',
                                                               'y_title': 'Power'
                                                              })
iplot(plot.figure)

[ ]:



[ ]: