Commit 6172143f by Armen Donigian

Build test v.4.

parent bfd7894b
......@@ -37,6 +37,7 @@ USER $NB_USER
# Expose the notebook port
EXPOSE 8888
#RUN . activate py36_oreilly_ml_prod_course
# Start the notebook server
CMD jupyter notebook --no-browser --port 8888 --ip=* --NotebookApp.token='' --NotebookApp.disable_check_xsrf=True --NotebookApp.iopub_data_rate_limit=1.0e10
CMD [ "/bin/bash -c \"source activate py36_oreilly_ml_prod_course\" && jupyter notebook --no-browser --port 8888 --ip=* --NotebookApp.token='' --NotebookApp.disable_check_xsrf=True --NotebookApp.iopub_data_rate_limit=1.0e10"]
name: py36_oreilly_ml_prod_course
channels:
- defaults
dependencies:
- yaml=
- pip:
- awscli==1.15.53
- boto3==1.7.52
- botocore==1.10.52
- cachetools==2.1.0
- clipper-admin
- configparser==3.5.0
- databricks-cli
- docker==3.4.1
- docker-pycreds==0.3.0
- gitdb2==2.0.3
- gitpython==2.1.10
- google==2.0.1
- google-auth==1.5.0
- gunicorn==19.9.0
- iml==0.6.1
- ipaddress==1.0.22
- jmespath==0.9.3
- joblib==0.12.1
- kubernetes==6.0.0
- mleap==0.8.1
- mlflow
- msgpack==0.5.6
- nose-exclude==0.5.0
- oauthlib==2.1.0
- prometheus-client==0.3.0
- protobuf==3.6.0
- pyasn1==0.4.3
- pyasn1-modules==0.2.2
- querystring-parser==1.2.3
- redis==2.10.6
- requests-oauthlib==1.0.0
- rsa==3.4.2
- s3transfer==0.1.13
- shap==0.19.2
- smmap2==2.0.3
- tabulate==0.8.2
- tqdm==4.23.4
- uuid==1.30
- websocket-client==0.48.0
- xgboost
- dvc
\ No newline at end of file
......@@ -247,11 +247,13 @@ dependencies:
- zlib=1.2.11=hf3cbc9b_2
- pip:
- arrow==0.12.1
- asciicanvas==0.0.3
- awscli==1.15.53
- binaryornot==0.4.4
- boto3==1.7.52
- botocore==1.10.52
- cachetools==2.1.0
- category-encoders==1.2.8
- clipper-admin==develop
- configobj==5.0.6
- configparser==3.5.0
......@@ -259,25 +261,30 @@ dependencies:
- databricks-cli==0.8.1
- docker==3.4.1
- docker-pycreds==0.3.0
- dvc==0.18.15
- future==0.16.0
- gitdb2==2.0.3
- gitpython==2.1.10
- google==2.0.1
- google-auth==1.5.0
- grandalf==0.6
- gunicorn==19.9.0
- iml==0.6.1
- ipaddress==1.0.22
- jinja2-time==0.2.0
- jmespath==0.9.3
- joblib==0.12.1
- jsonpath-rw==1.4.0
- kubernetes==6.0.0
- lime==0.1.1.32
- mleap==0.8.1
- mlflow==0.4.2
- msgpack==0.5.6
- nanotime==0.5.2
- nose-exclude==0.5.0
- ntfsutils==0.1.4
- oauthlib==2.1.0
- pandas-profiling==1.4.1
- poyo==0.4.1
- prometheus-client==0.3.0
- protobuf==3.6.0
......@@ -285,10 +292,13 @@ dependencies:
- pyasn1-modules==0.2.2
- querystring-parser==1.2.3
- redis==2.10.6
- reflink==0.2.0
- requests-oauthlib==1.0.0
- rsa==3.4.2
- s3transfer==0.1.13
- shap==0.19.2
- schema==0.6.8
- shap==0.23.1
- simplejson==3.16.0
- smmap2==2.0.3
- tables==3.4.3
- tabulate==0.8.2
......@@ -298,4 +308,3 @@ dependencies:
- whichcraft==0.4.1
- xgboost==0.72
- zc.lockfile==1.3.0
name: py36_oreilly_ml_prod_course
channels:
- defaults
dependencies:
- alabaster=0.7.10=py36h174008c_0
- anaconda=5.2.0=py36_3
- anaconda-client=1.6.14=py36_0
- anaconda-project=0.8.2=py36h9ee5d53_0
- appnope=0.1.0=py36hf537a9a_0
- appscript=1.0.1=py36h9e71e49_1
- asn1crypto=0.24.0=py36_0
- astroid=1.6.3=py36_0
- astropy=3.0.2=py36h917ab60_1
- attrs=18.1.0=py36_0
- babel=2.5.3=py36_0
- backcall=0.1.0=py36_0
- backports=1.0=py36ha3c1827_1
- backports.shutil_get_terminal_size=1.0.0=py36hd7a2ee4_2
- beautifulsoup4=4.6.0=py36h72d3c9f_1
- bitarray=0.8.1=py36h1de35cc_1
- bkcharts=0.2=py36h073222e_0
- blas=1.0=mkl
- blaze=0.11.3=py36h02e7a37_0
- bleach=2.1.3=py36_0
- blosc=1.14.3=hd9629dc_0
- bokeh=0.12.16=py36_0
- boto=2.48.0=py36hdbc59ac_1
- bottleneck=1.2.1=py36hbd380ad_0
- bzip2=1.0.6=h1de35cc_5
- ca-certificates=2018.03.07=0
- certifi=2018.4.16=py36_0
- cffi=1.11.5=py36h342bebf_0
- chardet=3.0.4=py36h96c241c_1
- click=6.7=py36hec950be_0
- cloudpickle=0.5.3=py36_0
- clyent=1.2.2=py36hae3ad88_0
- colorama=0.3.9=py36hd29a30c_0
- contextlib2=0.5.5=py36hd66e5e7_0
- cryptography=2.2.2=py36h1de35cc_0
- curl=7.60.0=ha441bb4_0
- cycler=0.10.0=py36hfc81398_0
- cython=0.28.2=py36h1de35cc_0
- cytoolz=0.9.0.1=py36h1de35cc_0
- dask=0.17.5=py36_0
- dask-core=0.17.5=py36_0
- datashape=0.5.4=py36hfb22df8_0
- dbus=1.13.2=h760590f_1
- decorator=4.3.0=py36_0
- distributed=1.21.8=py36_0
- docutils=0.14=py36hbfde631_0
- entrypoints=0.2.3=py36hd81d71f_2
- et_xmlfile=1.0.1=py36h1315bdc_0
- expat=2.2.5=hb8e80ba_0
- fastcache=1.0.2=py36h1de35cc_2
- filelock=3.0.4=py36_0
- flask=1.0.2=py36_1
- flask-cors=3.0.4=py36_0
- freetype=2.8=h12048fb_1
- get_terminal_size=1.0.0=h7520d66_0
- gettext=0.19.8.1=h15daf44_3
- gevent=1.3.0=py36h1de35cc_0
- glib=2.56.1=h35bc53a_0
- glob2=0.6=py36h94c9186_0
- gmp=6.1.2=hb37e062_1
- gmpy2=2.0.8=py36hf9c35bd_2
- greenlet=0.4.13=py36h1de35cc_0
- h5py=2.7.1=py36ha8ecd60_2
- hdf5=1.10.2=hfa1e0ec_1
- heapdict=1.0.0=py36_2
- html5lib=1.0.1=py36h2f9c1c0_0
- icu=58.2=h4b95b61_1
- idna=2.6=py36h8628d0a_1
- imageio=2.3.0=py36_0
- imagesize=1.0.0=py36_0
- intel-openmp=2018.0.0=8
- ipykernel=4.8.2=py36_0
- ipython=6.4.0=py36_0
- ipython_genutils=0.2.0=py36h241746c_0
- ipywidgets=7.2.1=py36_0
- isort=4.3.4=py36_0
- itsdangerous=0.24=py36h49fbb8d_1
- jbig=2.1=h4d881f8_0
- jdcal=1.4=py36_0
- jedi=0.12.0=py36_1
- jinja2=2.10=py36hd36f9c5_0
- jpeg=9b=he5867d9_2
- jsonschema=2.6.0=py36hb385e00_0
- jupyter=1.0.0=py36_4
- jupyter_client=5.2.3=py36_0
- jupyter_console=5.2.0=py36hccf5b1c_1
- jupyter_core=4.4.0=py36h79cf704_0
- jupyterlab=0.32.1=py36_0
- jupyterlab_launcher=0.10.5=py36_0
- kiwisolver=1.0.1=py36h792292d_0
- lazy-object-proxy=1.3.1=py36h2fbbe47_0
- libcurl=7.60.0=hf30b1f0_0
- libcxx=4.0.1=h579ed51_0
- libcxxabi=4.0.1=hebd6815_0
- libedit=3.1.20170329=hb402a30_2
- libffi=3.2.1=h475c297_4
- libgfortran=3.0.1=h93005f0_2
- libiconv=1.15=hdd342a3_7
- libpng=1.6.34=he12f830_0
- libsodium=1.0.16=h3efe00b_0
- libssh2=1.8.0=h322a93b_4
- libtiff=4.0.9=hcb84e12_1
- libxml2=2.9.8=hab757c2_1
- libxslt=1.1.32=hb819dd2_0
- llvmlite=0.23.1=py36hc454e04_0
- locket=0.2.0=py36hca03003_1
- lxml=4.2.1=py36h7166777_0
- lzo=2.10=h362108e_2
- markupsafe=1.0=py36h3a1e703_1
- matplotlib=2.2.2=py36ha7267d0_0
- mccabe=0.6.1=py36hdaeb55d_0
- mistune=0.8.3=py36h1de35cc_1
- mkl=2018.0.2=1
- mkl-service=1.1.2=py36h7ea6df4_4
- mkl_fft=1.0.1=py36h917ab60_0
- mkl_random=1.0.1=py36h78cc56f_0
- more-itertools=4.1.0=py36_0
- mpc=1.0.3=h7a72875_5
- mpfr=3.1.5=h711e7fd_2
- mpmath=1.0.0=py36hf1b8295_2
- msgpack-python=0.5.6=py36h04f5b5a_0
- multipledispatch=0.5.0=py36_0
- nbconvert=5.3.1=py36h810822e_0
- nbformat=4.4.0=py36h827af21_0
- ncurses=6.1=h0a44026_0
- networkx=2.1=py36_0
- nltk=3.3.0=py36_0
- nose=1.3.7=py36h73fae2b_2
- notebook=5.5.0=py36_0
- numba=0.38.0=py36h1702cab_0
- numexpr=2.6.5=py36h057f876_0
- numpy=1.14.3=py36h9bb19eb_1
- numpy-base=1.14.3=py36h479e554_1
- numpydoc=0.8.0=py36_0
- odo=0.5.1=py36hc1af34a_0
- olefile=0.45.1=py36_0
- openpyxl=2.5.3=py36_0
- openssl=1.0.2o=h26aff7b_0
- packaging=17.1=py36_0
- pandas=0.23.0=py36h1702cab_0
- pandoc=1.19.2.1=ha5e8f32_1
- pandocfilters=1.4.2=py36h3b0b094_1
- parso=0.2.0=py36_0
- partd=0.3.8=py36hf5c4cb8_0
- path.py=11.0.1=py36_0
- pathlib2=2.3.2=py36_0
- patsy=0.5.0=py36_0
- pcre=8.42=h378b8a2_0
- pep8=1.7.1=py36_0
- pexpect=4.5.0=py36_0
- pickleshare=0.7.4=py36hf512f8e_0
- pillow=5.1.0=py36hfcce615_0
- pip=10.0.1=py36_0
- pkginfo=1.4.2=py36_1
- pluggy=0.6.0=py36hb1d0581_0
- ply=3.11=py36_0
- prompt_toolkit=1.0.15=py36haeda067_0
- psutil=5.4.5=py36h1de35cc_0
- ptyprocess=0.5.2=py36he6521c3_0
- py=1.5.3=py36_0
- pycodestyle=2.4.0=py36_0
- pycosat=0.6.3=py36hee92d8f_0
- pycparser=2.18=py36h724b2fc_1
- pycrypto=2.6.1=py36h1de35cc_8
- pycurl=7.43.0.1=py36hdbc3d79_0
- pyflakes=1.6.0=py36hea45e83_0
- pygments=2.2.0=py36h240cd3f_0
- pylint=1.8.4=py36_0
- pyodbc=4.0.23=py36h0a44026_0
- pyopenssl=18.0.0=py36_0
- pyparsing=2.2.0=py36hb281f35_0
- pyqt=5.9.2=py36h11d3b92_0
- pysocks=1.6.8=py36_0
- pytables=3.4.3=py36h5ca999c_2
- pytest=3.5.1=py36_0
- pytest-arraydiff=0.2=py36_0
- pytest-astropy=0.3.0=py36_0
- pytest-doctestplus=0.1.3=py36_0
- pytest-openfiles=0.3.0=py36_0
- pytest-remotedata=0.2.1=py36_0
- python=3.6.5=hc167b69_1
- python-dateutil=2.7.3=py36_0
- python.app=2=py36_8
- pytz=2018.4=py36_0
- pywavelets=0.5.2=py36h2710a04_0
- pyyaml=3.12=py36h2ba1e63_1
- pyzmq=17.0.0=py36h1de35cc_1
- qt=5.9.5=h02808f3_0
- qtawesome=0.4.4=py36h468c6fb_0
- qtconsole=4.3.1=py36hd96c0ff_0
- qtpy=1.4.1=py36_0
- readline=7.0=hc1231fa_4
- requests=2.18.4=py36h4516966_1
- rope=0.10.7=py36h68959ac_0
- ruamel_yaml=0.15.35=py36h1de35cc_1
- scikit-image=0.13.1=py36h1de35cc_1
- scikit-learn=0.19.1=py36hffbff8c_0
- scipy=1.1.0=py36hcaad992_0
- seaborn=0.8.1=py36h595ecd9_0
- send2trash=1.5.0=py36_0
- setuptools=39.1.0=py36_0
- simplegeneric=0.8.1=py36_2
- singledispatch=3.4.0.3=py36hf20db9d_0
- sip=4.19.8=py36h0a44026_0
- six=1.11.0=py36h0e22d5e_1
- snappy=1.1.7=he62c110_3
- snowballstemmer=1.2.1=py36h6c7b616_0
- sortedcollections=0.6.1=py36_0
- sortedcontainers=1.5.10=py36_0
- sphinx=1.7.4=py36_0
- sphinxcontrib=1.0=py36h9364dc8_1
- sphinxcontrib-websupport=1.0.1=py36h92f4a7a_1
- spyder=3.2.8=py36_0
- sqlalchemy=1.2.7=py36hb402a30_0
- sqlite=3.23.1=hf1716c9_0
- statsmodels=0.9.0=py36h917ab60_0
- sympy=1.1.1=py36h7f3cf04_0
- tblib=1.3.2=py36hda67792_0
- terminado=0.8.1=py36_1
- testpath=0.3.1=py36h625a49b_0
- tk=8.6.7=h35a86e2_3
- toolz=0.9.0=py36_0
- tornado=5.0.2=py36_0
- traitlets=4.3.2=py36h65bd3ce_0
- typing=3.6.4=py36_0
- unicodecsv=0.14.1=py36he531d66_0
- unixodbc=2.3.6=h3efe00b_0
- urllib3=1.22=py36h68b9469_0
- wcwidth=0.1.7=py36h8c6ec74_0
- webencodings=0.5.1=py36h3b9701d_1
- werkzeug=0.14.1=py36_0
- wheel=0.31.1=py36_0
- widgetsnbextension=3.2.1=py36_0
- wrapt=1.10.11=py36hc29e774_0
- xlrd=1.1.0=py36h336f4a2_1
- xlsxwriter=1.0.4=py36_0
- xlwings=0.11.8=py36_0
- xlwt=1.2.0=py36h5ad1178_0
- xz=5.2.4=h1de35cc_4
- yaml=0.1.7=hc338f04_2
- zeromq=4.2.5=h378b8a2_0
- zict=0.1.3=py36h71da714_0
- zlib=1.2.11=hf3cbc9b_2
- pip:
- awscli==1.15.53
- boto3==1.7.52
- botocore==1.10.52
- cachetools==2.1.0
- clipper-admin==develop
- configparser==3.5.0
- databricks-cli==0.7.2
- docker==3.4.1
- docker-pycreds==0.3.0
- gitdb2==2.0.3
- gitpython==2.1.10
- google==2.0.1
- google-auth==1.5.0
- gunicorn==19.9.0
- iml==0.6.1
- ipaddress==1.0.22
- jmespath==0.9.3
- joblib==0.12.1
- kubernetes==6.0.0
- mleap==0.8.1
- mlflow==0.2.1
- msgpack==0.5.6
- nose-exclude==0.5.0
- oauthlib==2.1.0
- prometheus-client==0.3.0
- protobuf==3.6.0
- pyasn1==0.4.3
- pyasn1-modules==0.2.2
- querystring-parser==1.2.3
- redis==2.10.6
- requests-oauthlib==1.0.0
- rsa==3.4.2
- s3transfer==0.1.13
- shap==0.19.2
- smmap2==2.0.3
- tables==3.4.3
- tabulate==0.8.2
- tqdm==4.23.4
- uuid==1.30
- websocket-client==0.48.0
- xgboost==0.72
......@@ -11790,79 +11790,7 @@ div#notebook {
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[1]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>wget https://raw.githubusercontent.com/jeroenjanssens/data-science-at-the-command-line/master/tools/csv2vw
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="prompt"></div>
<div class="output_subarea output_stream output_stdout output_text">
<pre>--2018-09-10 22:21:31-- https://raw.githubusercontent.com/jeroenjanssens/data-science-at-the-command-line/master/tools/csv2vw
Resolving raw.githubusercontent.com... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...
Connecting to raw.githubusercontent.com|151.101.0.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 5464 (5.3K) [text/plain]
Saving to: ‘csv2vw’
csv2vw 100%[===================&gt;] 5.34K --.-KB/s in 0s
2018-09-10 22:21:32 (21.7 MB/s) - ‘csv2vw’ saved [5464/5464]
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[2]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>pwd
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="prompt"></div>
<div class="output_subarea output_stream output_stdout output_text">
<pre>/Users/arm/code/ML_Models_to_Production/notebooks
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[3]:</div>
<div class="prompt input_prompt">In&nbsp;[13]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">import</span> <span class="nn">logging</span><span class="o">,</span> <span class="nn">xgboost</span> <span class="k">as</span> <span class="nn">xgb</span><span class="o">,</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
......@@ -11907,7 +11835,7 @@ csv2vw 100%[===================&gt;] 5.34K --.-KB/s in 0s
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[4]:</div>
<div class="prompt input_prompt">In&nbsp;[14]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">train</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
......@@ -11923,7 +11851,7 @@ csv2vw 100%[===================&gt;] 5.34K --.-KB/s in 0s
<div class="output_area">
<div class="prompt output_prompt">Out[4]:</div>
<div class="prompt output_prompt">Out[14]:</div>
......@@ -12104,7 +12032,7 @@ csv2vw 100%[===================&gt;] 5.34K --.-KB/s in 0s
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[5]:</div>
<div class="prompt input_prompt">In&nbsp;[15]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">train</span><span class="o">.</span><span class="n">columns</span>
......@@ -12120,7 +12048,7 @@ csv2vw 100%[===================&gt;] 5.34K --.-KB/s in 0s
<div class="output_area">
<div class="prompt output_prompt">Out[5]:</div>
<div class="prompt output_prompt">Out[15]:</div>
......@@ -12144,7 +12072,7 @@ csv2vw 100%[===================&gt;] 5.34K --.-KB/s in 0s
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[6]:</div>
<div class="prompt input_prompt">In&nbsp;[16]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>csv2vw --help
......@@ -12216,7 +12144,7 @@ Usage: csv2vw [options] [&lt;label_column&gt;] files...
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[7]:</div>
<div class="prompt input_prompt">In&nbsp;[17]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>csv2vw -h -- -1 ../data/processed/train.csv &gt; ../data/processed/train.vw
......@@ -12229,7 +12157,7 @@ Usage: csv2vw [options] [&lt;label_column&gt;] files...
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[8]:</div>
<div class="prompt input_prompt">In&nbsp;[18]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>head ../data/processed/train.vw
......@@ -12269,7 +12197,7 @@ Usage: csv2vw [options] [&lt;label_column&gt;] files...
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[9]:</div>
<div class="prompt input_prompt">In&nbsp;[19]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>sed <span class="s1">&#39;s/^2 /-1 /g&#39;</span> ../data/processed/train.vw &gt; ../data/processed/train_transformed.vw
......@@ -12282,7 +12210,7 @@ Usage: csv2vw [options] [&lt;label_column&gt;] files...
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[10]:</div>
<div class="prompt input_prompt">In&nbsp;[20]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>head ../data/processed/train_transformed.vw
......@@ -12322,7 +12250,7 @@ Usage: csv2vw [options] [&lt;label_column&gt;] files...
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[11]:</div>
<div class="prompt input_prompt">In&nbsp;[21]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>vw --help
......@@ -12495,7 +12423,7 @@ Output model:
with numeric features
--invert_hash arg Output human-readable final regressor
with feature names. Computationally
expensive.
--save_resume save extra state so learning can be
resumed later with new data
--preserve_performance_counters reset performance counters when
......@@ -12706,7 +12634,7 @@ Cost-sensitive Active Learning:
domination. Default 1
--mellowness arg (=0.100000001) mellowness parameter c_0. Default 0.1.
--range_c arg (=0.5) parameter controlling the threshold for
per-label cost uncertainty. Default
0.5.
--max_labels arg (=18446744073709551615)
maximum number of label queries.
......@@ -13037,7 +12965,7 @@ Input options:
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[12]:</div>
<div class="prompt input_prompt">In&nbsp;[22]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>vw <span class="err">\</span>
......
......@@ -21,51 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--2018-09-10 22:21:31-- https://raw.githubusercontent.com/jeroenjanssens/data-science-at-the-command-line/master/tools/csv2vw\n",
"Resolving raw.githubusercontent.com... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...\n",
"Connecting to raw.githubusercontent.com|151.101.0.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 5464 (5.3K) [text/plain]\n",
"Saving to: ‘csv2vw’\n",
"\n",
"csv2vw 100%[===================>] 5.34K --.-KB/s in 0s \n",
"\n",
"2018-09-10 22:21:32 (21.7 MB/s) - ‘csv2vw’ saved [5464/5464]\n",
"\n"
]
}
],
"source": [
"!wget https://raw.githubusercontent.com/jeroenjanssens/data-science-at-the-command-line/master/tools/csv2vw"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/Users/arm/code/ML_Models_to_Production/notebooks\r\n"
]
}
],
"source": [
"!pwd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 13,
"metadata": {},
"outputs": [
{
......@@ -96,7 +52,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 14,
"metadata": {},
"outputs": [
{
......@@ -301,7 +257,7 @@
"[5 rows x 32 columns]"
]
},
"execution_count": 4,
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
......@@ -312,7 +268,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 15,
"metadata": {},
"outputs": [
{
......@@ -328,7 +284,7 @@
" dtype='object')"
]
},
"execution_count": 5,
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
......@@ -339,7 +295,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 16,
"metadata": {},
"outputs": [
{
......@@ -397,7 +353,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
......@@ -406,7 +362,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 18,
"metadata": {},
"outputs": [
{
......@@ -432,7 +388,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
......@@ -441,7 +397,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 20,
"metadata": {},
"outputs": [
{
......@@ -467,7 +423,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 21,
"metadata": {},
"outputs": [
{
......@@ -627,7 +583,8 @@
" with numeric features\r\n",
" --invert_hash arg Output human-readable final regressor \r\n",
" with feature names. Computationally \r\n",
" expensive.\r\n",
" expensive.\r",
"\r\n",
" --save_resume save extra state so learning can be \r\n",
" resumed later with new data\r\n",
" --preserve_performance_counters reset performance counters when \r\n",
......@@ -838,7 +795,8 @@