Skip to content

Instantly share code, notes, and snippets.

@FavioVazquez

FavioVazquez/Test_fklearn.ipynb

Created May 2, 2019 21:34
Show Gist options
  • Save FavioVazquez/1900695037b5b9490f76b130bb4f5cb9 to your computer and use it in GitHub Desktop.
Save FavioVazquez/1900695037b5b9490f76b130bb4f5cb9 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Test_fklearn.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting fklearn\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/ac/0b/8f7e380ed15ce04370d2160928c338506fa8b13f4f10fd423aec9058f536/fklearn-1.14.0-py3-none-any.whl (57kB)\n",
"\u001b[K 100% |████████████████████████████████| 61kB 1.2MB/s \n",
"\u001b[?25hCollecting lightgbm<3,>=2.2.2 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/77/0f/5157e6b153b3d4a70dc5fbe2ab6f209604197590f387f03177b7a249ac60/lightgbm-2.2.3-py2.py3-none-manylinux1_x86_64.whl (1.2MB)\n",
"\u001b[K 100% |████████████████████████████████| 1.2MB 1.9MB/s \n",
"\u001b[?25hCollecting swifter<0.300,>=0.284 (from fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/1e/5b/aad4d173522a7b5578b7d5c9e8cd2d6c49f3bb9a23895fa16b6283495b2b/swifter-0.287.tar.gz\n",
"Collecting shap<1,>=0.28.5 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/30/b3/866b0101cbd1829844c35964af68c14ba522a5cce7a1e8d0f7937411d910/shap-0.28.5.tar.gz (223kB)\n",
"\u001b[K 100% |████████████████████████████████| 225kB 3.6MB/s \n",
"\u001b[?25hCollecting joblib<1,>=0.13.2 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/cd/c1/50a758e8247561e58cb87305b1e90b171b8c767b15b12a1734001f41d356/joblib-0.13.2-py2.py3-none-any.whl (278kB)\n",
"\u001b[K 100% |████████████████████████████████| 286kB 4.3MB/s \n",
"\u001b[?25hCollecting pyarrow<1,>=0.12.0 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/ad/25/094b122d828d24b58202712a74e661e36cd551ca62d331e388ff68bae91d/pyarrow-0.13.0-cp36-cp36m-manylinux1_x86_64.whl (48.5MB)\n",
"\u001b[K 100% |████████████████████████████████| 48.5MB 152kB/s \n",
"\u001b[?25hCollecting tqdm<5,>=4.31.1 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/6c/4b/c38b5144cf167c4f52288517436ccafefe9dc01b8d1c190e18a6b154cd4a/tqdm-4.31.1-py2.py3-none-any.whl (48kB)\n",
"\u001b[K 100% |████████████████████████████████| 51kB 1.9MB/s \n",
"\u001b[?25hRequirement already satisfied: pandas<0.25,>=0.24.1 in /opt/conda/lib/python3.6/site-packages (from fklearn) (0.24.1)\n",
"Requirement already satisfied: numpy<2,>=1.15.4 in /opt/conda/lib/python3.6/site-packages (from fklearn) (1.16.2)\n",
"Collecting xgboost<1,>=0.81 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/6a/49/7e10686647f741bd9c8918b0decdb94135b542fe372ca1100739b8529503/xgboost-0.82-py2.py3-none-manylinux1_x86_64.whl (114.0MB)\n",
"\u001b[K 100% |████████████████████████████████| 114.0MB 65kB/s \n",
"\u001b[?25hCollecting scikit-image<1,>=0.14.2 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/d4/ab/674e168bf7d0bc597218b3bec858d02c23fbac9ec1fec9cad878c6cee95f/scikit_image-0.15.0-cp36-cp36m-manylinux1_x86_64.whl (26.3MB)\n",
"\u001b[K 100% |████████████████████████████████| 26.3MB 257kB/s \n",
"\u001b[?25hRequirement already satisfied: matplotlib<4,>=3.0.2 in /opt/conda/lib/python3.6/site-packages (from fklearn) (3.0.2)\n",
"Requirement already satisfied: cloudpickle<1,>=0.8.0 in /opt/conda/lib/python3.6/site-packages (from fklearn) (0.8.0)\n",
"Collecting schema<1,>=0.6.2 (from fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/74/f5/a14c01bcc9dbf99fd164fe2c55229569456f991a162daf62d3275714d241/schema-0.7.0-py2.py3-none-any.whl\n",
"Requirement already satisfied: scikit-learn<1,>=0.20.2 in /opt/conda/lib/python3.6/site-packages (from fklearn) (0.20.2)\n",
"Requirement already satisfied: statsmodels<1,>=0.9.0 in /opt/conda/lib/python3.6/site-packages (from fklearn) (0.9.0)\n",
"Collecting boto3<2,>=1.7.24 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/51/99/cef419ab955dde1c35d24c4c8dca3f76c72bc81605af6ca36394871fbaa8/boto3-1.9.141-py2.py3-none-any.whl (128kB)\n",
"\u001b[K 100% |████████████████████████████████| 133kB 3.7MB/s \n",
"\u001b[?25hCollecting catboost<1,>=0.14.2 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/2f/c4/f130237b24efd1941cb685da12496675a90045129b66774751f1bf629dfd/catboost-0.14.2-cp36-none-manylinux1_x86_64.whl (60.6MB)\n",
"\u001b[K 100% |████████████████████████████████| 60.6MB 112kB/s \n",
"\u001b[?25hRequirement already satisfied: toolz<1,>=0.9.0 in /opt/conda/lib/python3.6/site-packages (from fklearn) (0.9.0)\n",
"Collecting s3fs<1,>=0.2.0 (from fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/68/8a/a2430bda6106aaaee6d53fa9be914ff3023d3f9d547b959a47641addad33/s3fs-0.2.1.tar.gz (46kB)\n",
"\u001b[K 100% |████████████████████████████████| 51kB 1.9MB/s \n",
"\u001b[?25hRequirement already satisfied: scipy in /opt/conda/lib/python3.6/site-packages (from lightgbm<3,>=2.2.2->fklearn) (1.2.1)\n",
"Collecting psutil (from swifter<0.300,>=0.284->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/c6/c1/beed5e4eaa1345901b595048fab1c85aee647ea0fc02d9e8bf9aceb81078/psutil-5.6.2.tar.gz (432kB)\n",
"\u001b[K 100% |████████████████████████████████| 440kB 3.2MB/s \n",
"\u001b[?25hRequirement already satisfied: dask[complete]>=0.19.0 in /opt/conda/lib/python3.6/site-packages (from swifter<0.300,>=0.284->fklearn) (1.1.2)\n",
"Requirement already satisfied: ipywidgets>=7.0.0 in /opt/conda/lib/python3.6/site-packages (from swifter<0.300,>=0.284->fklearn) (7.4.2)\n",
"Requirement already satisfied: numba in /opt/conda/lib/python3.6/site-packages (from swifter<0.300,>=0.284->fklearn) (0.42.0)\n",
"Requirement already satisfied: ipython in /opt/conda/lib/python3.6/site-packages (from shap<1,>=0.28.5->fklearn) (7.3.0)\n",
"Requirement already satisfied: six>=1.0.0 in /opt/conda/lib/python3.6/site-packages (from pyarrow<1,>=0.12.0->fklearn) (1.12.0)\n",
"Requirement already satisfied: python-dateutil>=2.5.0 in /opt/conda/lib/python3.6/site-packages (from pandas<0.25,>=0.24.1->fklearn) (2.8.0)\n",
"Requirement already satisfied: pytz>=2011k in /opt/conda/lib/python3.6/site-packages (from pandas<0.25,>=0.24.1->fklearn) (2018.9)\n",
"Requirement already satisfied: networkx>=2.0 in /opt/conda/lib/python3.6/site-packages (from scikit-image<1,>=0.14.2->fklearn) (2.2)\n",
"Requirement already satisfied: PyWavelets>=0.4.0 in /opt/conda/lib/python3.6/site-packages (from scikit-image<1,>=0.14.2->fklearn) (1.0.1)\n",
"Requirement already satisfied: pillow>=4.3.0 in /opt/conda/lib/python3.6/site-packages (from scikit-image<1,>=0.14.2->fklearn) (5.4.1)\n",
"Requirement already satisfied: imageio>=2.0.1 in /opt/conda/lib/python3.6/site-packages (from scikit-image<1,>=0.14.2->fklearn) (2.5.0)\n",
"Requirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.6/site-packages (from matplotlib<4,>=3.0.2->fklearn) (0.10.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/lib/python3.6/site-packages (from matplotlib<4,>=3.0.2->fklearn) (1.0.1)\n",
"Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /opt/conda/lib/python3.6/site-packages (from matplotlib<4,>=3.0.2->fklearn) (2.3.1)\n",
"Collecting contextlib2==0.5.5 (from schema<1,>=0.6.2->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/a2/71/8273a7eeed0aff6a854237ab5453bc9aa67deb49df4832801c21f0ff3782/contextlib2-0.5.5-py2.py3-none-any.whl\n",
"Collecting s3transfer<0.3.0,>=0.2.0 (from boto3<2,>=1.7.24->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/d7/de/5737f602e22073ecbded7a0c590707085e154e32b68d86545dcc31004c02/s3transfer-0.2.0-py2.py3-none-any.whl (69kB)\n",
"\u001b[K 100% |████████████████████████████████| 71kB 2.2MB/s \n",
"\u001b[?25hCollecting botocore<1.13.0,>=1.12.141 (from boto3<2,>=1.7.24->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/af/72/bb5092d4f8a7b6c9a4508b784cdfed6d856e2a202383c345a66da71cc612/botocore-1.12.141-py2.py3-none-any.whl (5.4MB)\n",
"\u001b[K 100% |████████████████████████████████| 5.4MB 1.3MB/s \n",
"\u001b[?25hCollecting jmespath<1.0.0,>=0.7.1 (from boto3<2,>=1.7.24->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/83/94/7179c3832a6d45b266ddb2aac329e101367fbdb11f425f13771d27f225bb/jmespath-0.9.4-py2.py3-none-any.whl\n",
"Collecting enum34 (from catboost<1,>=0.14.2->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/af/42/cb9355df32c69b553e72a2e28daee25d1611d2c0d9c272aa1d34204205b2/enum34-1.1.6-py3-none-any.whl\n",
"Collecting graphviz (from catboost<1,>=0.14.2->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/1f/e2/ef2581b5b86625657afd32030f90cf2717456c1d2b711ba074bf007c0f1a/graphviz-0.10.1-py2.py3-none-any.whl\n",
"Collecting distributed>=1.22; extra == \"complete\" (from dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/14/37/560b694bc2fe80c04bb64e3959e29afda4f7ed715726e357b05f01cfe07e/distributed-1.27.1-py2.py3-none-any.whl (514kB)\n",
"\u001b[K 100% |████████████████████████████████| 522kB 2.5MB/s \n",
"\u001b[?25hCollecting partd>=0.3.8; extra == \"complete\" (from dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/9e/f5/c02903ad5a444c9f80e4d1fe4d512afd76e3801de2fba80ea9ed28f9290c/partd-0.3.10-py3-none-any.whl\n",
"Requirement already satisfied: widgetsnbextension~=3.4.0 in /opt/conda/lib/python3.6/site-packages (from ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (3.4.2)\n",
"Requirement already satisfied: traitlets>=4.3.1 in /opt/conda/lib/python3.6/site-packages (from ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (4.3.2)\n",
"Requirement already satisfied: ipykernel>=4.5.1 in /opt/conda/lib/python3.6/site-packages (from ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (5.1.0)\n",
"Requirement already satisfied: nbformat>=4.2.0 in /opt/conda/lib/python3.6/site-packages (from ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (4.4.0)\n",
"Requirement already satisfied: llvmlite>=0.27.0dev0 in /opt/conda/lib/python3.6/site-packages (from numba->swifter<0.300,>=0.284->fklearn) (0.27.0)\n",
"Requirement already satisfied: jedi>=0.10 in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (0.13.3)\n",
"Requirement already satisfied: setuptools>=18.5 in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (40.8.0)\n",
"Requirement already satisfied: pickleshare in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (0.7.5)\n",
"Requirement already satisfied: pexpect; sys_platform != \"win32\" in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (4.6.0)\n",
"Requirement already satisfied: prompt-toolkit<2.1.0,>=2.0.0 in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (2.0.9)\n",
"Requirement already satisfied: pygments in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (2.3.1)\n",
"Requirement already satisfied: decorator in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (4.3.2)\n",
"Requirement already satisfied: backcall in /opt/conda/lib/python3.6/site-packages (from ipython->shap<1,>=0.28.5->fklearn) (0.1.0)\n",
"Requirement already satisfied: urllib3<1.25,>=1.20; python_version >= \"3.4\" in /opt/conda/lib/python3.6/site-packages (from botocore<1.13.0,>=1.12.141->boto3<2,>=1.7.24->fklearn) (1.24.1)\n",
"Collecting docutils>=0.10 (from botocore<1.13.0,>=1.12.141->boto3<2,>=1.7.24->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/36/fa/08e9e6e0e3cbd1d362c3bbee8d01d0aedb2155c4ac112b19ef3cae8eed8d/docutils-0.14-py3-none-any.whl (543kB)\n",
"\u001b[K 100% |████████████████████████████████| 552kB 2.7MB/s \n",
"\u001b[?25hCollecting tblib (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/64/b5/ebb1af4d843047ccd7292b92f5e5f8643153e8b95d14508d9fe3b35f7004/tblib-1.4.0-py2.py3-none-any.whl\n",
"Collecting zict>=0.1.3 (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/bd/45/a2e6f95a850cd407d785f2f8624b02e72baf6ab910aea4bdcac7e18b4871/zict-0.1.4-py2.py3-none-any.whl\n",
"Requirement already satisfied: pyyaml in /opt/conda/lib/python3.6/site-packages (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn) (3.13)\n",
"Collecting sortedcontainers!=2.0.0,!=2.0.1 (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/13/f3/cf85f7c3a2dbd1a515d51e1f1676d971abe41bba6f4ab5443240d9a78e5b/sortedcontainers-2.1.0-py2.py3-none-any.whl\n",
"Collecting msgpack (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/92/7e/ae9e91c1bb8d846efafd1f353476e3fd7309778b582d2fb4cea4cc15b9a2/msgpack-0.6.1-cp36-cp36m-manylinux1_x86_64.whl (248kB)\n",
"\u001b[K 100% |████████████████████████████████| 256kB 2.3MB/s \n",
"\u001b[?25hCollecting click>=6.6 (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/fa/37/45185cb5abbc30d7257104c434fe0b07e5a195a6847506c074527aa599ec/Click-7.0-py2.py3-none-any.whl (81kB)\n",
"\u001b[K 100% |████████████████████████████████| 81kB 2.4MB/s \n",
"\u001b[?25hRequirement already satisfied: tornado>=5 in /opt/conda/lib/python3.6/site-packages (from distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn) (5.1.1)\n",
"Collecting locket (from partd>=0.3.8; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/d0/22/3c0f97614e0be8386542facb3a7dcfc2584f7b83608c02333bced641281c/locket-0.2.0.tar.gz\n",
"Requirement already satisfied: notebook>=4.4.1 in /opt/conda/lib/python3.6/site-packages (from widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (5.7.4)\n",
"Requirement already satisfied: ipython_genutils in /opt/conda/lib/python3.6/site-packages (from traitlets>=4.3.1->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.2.0)\n",
"Requirement already satisfied: jupyter-client in /opt/conda/lib/python3.6/site-packages (from ipykernel>=4.5.1->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (5.2.4)\n",
"Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in /opt/conda/lib/python3.6/site-packages (from nbformat>=4.2.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (2.6.0)\n",
"Requirement already satisfied: jupyter_core in /opt/conda/lib/python3.6/site-packages (from nbformat>=4.2.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (4.4.0)\n",
"Requirement already satisfied: parso>=0.3.0 in /opt/conda/lib/python3.6/site-packages (from jedi>=0.10->ipython->shap<1,>=0.28.5->fklearn) (0.3.4)\n",
"Requirement already satisfied: ptyprocess>=0.5 in /opt/conda/lib/python3.6/site-packages (from pexpect; sys_platform != \"win32\"->ipython->shap<1,>=0.28.5->fklearn) (0.6.0)\n",
"Requirement already satisfied: wcwidth in /opt/conda/lib/python3.6/site-packages (from prompt-toolkit<2.1.0,>=2.0.0->ipython->shap<1,>=0.28.5->fklearn) (0.1.7)\n",
"Collecting heapdict (from zict>=0.1.3->distributed>=1.22; extra == \"complete\"->dask[complete]>=0.19.0->swifter<0.300,>=0.284->fklearn)\n",
" Downloading https://files.pythonhosted.org/packages/e2/ca/f5feba2f939c97629dbce52a17acc95a0d10256ef620334795379dda8ce6/HeapDict-1.0.0.tar.gz\n",
"Requirement already satisfied: pyzmq>=17 in /opt/conda/lib/python3.6/site-packages (from notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (18.0.0)\n",
"Requirement already satisfied: terminado>=0.8.1 in /opt/conda/lib/python3.6/site-packages (from notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.8.1)\n",
"Requirement already satisfied: prometheus-client in /opt/conda/lib/python3.6/site-packages (from notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.6.0)\n",
"Requirement already satisfied: Send2Trash in /opt/conda/lib/python3.6/site-packages (from notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (1.5.0)\n",
"Requirement already satisfied: jinja2 in /opt/conda/lib/python3.6/site-packages (from notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (2.10)\n",
"Requirement already satisfied: nbconvert in /opt/conda/lib/python3.6/site-packages (from notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (5.3.1)\n",
"Requirement already satisfied: MarkupSafe>=0.23 in /opt/conda/lib/python3.6/site-packages (from jinja2->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (1.1.1)\n",
"Requirement already satisfied: mistune>=0.7.4 in /opt/conda/lib/python3.6/site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.8.4)\n",
"Requirement already satisfied: entrypoints>=0.2.2 in /opt/conda/lib/python3.6/site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.3)\n",
"Requirement already satisfied: bleach in /opt/conda/lib/python3.6/site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (3.1.0)\n",
"Requirement already satisfied: pandocfilters>=1.4.1 in /opt/conda/lib/python3.6/site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (1.4.2)\n",
"Requirement already satisfied: testpath in /opt/conda/lib/python3.6/site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.4.2)\n",
"Requirement already satisfied: webencodings in /opt/conda/lib/python3.6/site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.4.0->ipywidgets>=7.0.0->swifter<0.300,>=0.284->fklearn) (0.5.1)\n",
"Building wheels for collected packages: swifter, shap, s3fs, psutil, locket, heapdict\n",
" Building wheel for swifter (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Stored in directory: /home/matrix/.cache/pip/wheels/97/17/94/ff3415e88282ef0e435671f061c170c552671b9d3af75e96de\n",
" Building wheel for shap (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Stored in directory: /home/matrix/.cache/pip/wheels/bf/26/bd/912db1314f1cef0171d9b7f128dd01e8b8c92ed8d0062e632d\n",
" Building wheel for s3fs (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Stored in directory: /home/matrix/.cache/pip/wheels/f5/2d/de/6e81a0885c7c5c4731bfc8f1d27abf80414d3633d6d6b103ef\n",
" Building wheel for psutil (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Stored in directory: /home/matrix/.cache/pip/wheels/17/08/ec/22b464874958c3fc91e1a75748fae2220eb704a8b1035f9a03\n",
" Building wheel for locket (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Stored in directory: /home/matrix/.cache/pip/wheels/26/1e/e8/4fa236ec931b1a0cdd61578e20d4934d7bf188858723b84698\n",
" Building wheel for heapdict (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Stored in directory: /home/matrix/.cache/pip/wheels/40/b9/42/344857b482c954f48bcff6db72d388e30bf2bee4ed14706faa\n",
"Successfully built swifter shap s3fs psutil locket heapdict\n",
"Installing collected packages: lightgbm, psutil, tqdm, swifter, scikit-image, shap, joblib, pyarrow, xgboost, contextlib2, schema, docutils, jmespath, botocore, s3transfer, boto3, enum34, graphviz, catboost, s3fs, fklearn, tblib, heapdict, zict, sortedcontainers, msgpack, click, distributed, locket, partd\n",
"\u001b[33m The script tqdm is installed in '/home/matrix/.local/bin' which is not on PATH.\n",
" Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\n",
"\u001b[33m The script skivi is installed in '/home/matrix/.local/bin' which is not on PATH.\n",
" Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\n",
"\u001b[33m The script plasma_store is installed in '/home/matrix/.local/bin' which is not on PATH.\n",
" Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\n",
"\u001b[33m The scripts dask-mpi, dask-remote, dask-scheduler, dask-ssh, dask-submit and dask-worker are installed in '/home/matrix/.local/bin' which is not on PATH.\n",
" Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\n",
"Successfully installed boto3-1.9.141 botocore-1.12.141 catboost-0.14.2 click-7.0 contextlib2-0.5.5 distributed-1.27.1 docutils-0.14 enum34-1.1.6 fklearn-1.14.0 graphviz-0.10.1 heapdict-1.0.0 jmespath-0.9.4 joblib-0.13.2 lightgbm-2.2.3 locket-0.2.0 msgpack-0.6.1 partd-0.3.10 psutil-5.6.2 pyarrow-0.13.0 s3fs-0.2.1 s3transfer-0.2.0 schema-0.7.0 scikit-image-0.15.0 shap-0.28.5 sortedcontainers-2.1.0 swifter-0.287 tblib-1.4.0 tqdm-4.31.1 xgboost-0.82 zict-0.1.4\n"
]
}
],
"source": [
"!pip install --user fklearn"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import toolz as fp\n",
"import pandas as pd\n",
"import numpy as np\n",
"from matplotlib import pyplot as plt\n",
"import numpy.random as random\n",
"import sys\n",
"from importlib import reload\n",
"import shap"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def reload_all(target):\n",
" list(fp.map(lambda y: reload(sys.modules[y]) if sys.modules[y] else None, list(fp.remove(lambda x: target not in x, sys.modules.keys()))))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"reload_all('fklearn')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"import warnings\n",
"warnings.simplefilter(\"ignore\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"from fklearn.training.transformation import capper, floorer, prediction_ranger\n",
"from fklearn.training.pipeline import build_pipeline"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"from fklearn.validation.evaluators import mean_prediction_evaluator, r2_evaluator, mse_evaluator, combined_evaluators\n",
"from fklearn.validation.validator import validator\n",
"from fklearn.validation.splitters import k_fold_splitter, out_of_time_and_space_splitter\n",
"from fklearn.metrics.pd_extractors import evaluator_extractor as pd_evaluator_extractor, extract as pd_extract, \\\n",
" reverse_learning_curve_evaluator_extractor, evaluator_extractor, extract"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate random data"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"random.seed(131)\n",
"dates = pd.DataFrame( {\"score_date\": pd.date_range(\"2019-01-01\", \"2019-12-31\")} )\n",
"ids = pd.DataFrame( {\"id\": np.arange(0, 100)} )\n",
"\n",
"# make keys for cross join\n",
"dates[\"key\"] = 1\n",
"ids[\"key\"] = 1\n",
"\n",
"data = pd.merge(ids, dates).drop(\"key\", axis=1)\n",
"\n",
"data[\"x1\"] = 23*random.randn(data.shape[0]) + 500\n",
"data[\"x2\"] = 59*random.randn(data.shape[0]) + 235\n",
"# Noise Feature\n",
"data[\"x3\"] = 73*random.randn(data.shape[0]) + 793\n",
"data[\"y\"] = 0.37 * data[\"x1\"] +\\\n",
" 0.97*data[\"x2\"] + 0.32*data[\"x2\"]**2 -\\\n",
" 5 * data[\"id\"] * 0.2 +\\\n",
" np.cos(pd.to_datetime(data[\"score_date\"]).astype(int) * 200) * 20\n",
" \n",
"# inject NaNs\n",
"nan_idx = np.random.randint(0, data.shape[0], size=100)\n",
"data.loc[nan_idx, \"x1\"] = np.nan\n",
"\n",
"nan_idx = np.random.randint(0, data.shape[0], size=100)\n",
"data.loc[nan_idx, \"x2\"] = np.nan"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>score_date</th>\n",
" <th>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>2019-01-01</td>\n",
" <td>510.355134</td>\n",
" <td>236.471776</td>\n",
" <td>906.162151</td>\n",
" <td>18306.384983</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>2019-01-02</td>\n",
" <td>503.469826</td>\n",
" <td>226.489534</td>\n",
" <td>705.821412</td>\n",
" <td>16837.011069</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>2019-01-03</td>\n",
" <td>536.412361</td>\n",
" <td>187.096411</td>\n",
" <td>875.440154</td>\n",
" <td>11561.595513</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>2019-01-04</td>\n",
" <td>471.144774</td>\n",
" <td>225.913422</td>\n",
" <td>840.266189</td>\n",
" <td>16742.066653</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>2019-01-05</td>\n",
" <td>482.795605</td>\n",
" <td>333.892673</td>\n",
" <td>835.026821</td>\n",
" <td>36170.022285</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id score_date x1 x2 x3 y\n",
"0 0 2019-01-01 510.355134 236.471776 906.162151 18306.384983\n",
"1 0 2019-01-02 503.469826 226.489534 705.821412 16837.011069\n",
"2 0 2019-01-03 536.412361 187.096411 875.440154 11561.595513\n",
"3 0 2019-01-04 471.144774 225.913422 840.266189 16742.066653\n",
"4 0 2019-01-05 482.795605 333.892673 835.026821 36170.022285"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Split the data"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"from fklearn.preprocessing.splitting import space_time_split_dataset\n",
"train_start = \"2019-01-01\"\n",
"train_end = \"2019-06-30\"\n",
"holdout_end = \"2019-12-31\"\n",
"\n",
"split_fn = space_time_split_dataset(train_start_date=train_start,\n",
" train_end_date=train_end,\n",
" holdout_end_date=holdout_end,\n",
" split_seed=42, space_holdout_percentage=.05,\n",
" space_column=\"id\", time_column=\"score_date\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((17100, 6), (900, 6), (18400, 6), (920, 6))"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_set, intime_outspace_hdout, outime_inspace_hdout, outime_outspace_hdout = split_fn(data)\n",
"train_set.shape, intime_outspace_hdout.shape, outime_inspace_hdout.shape, outime_outspace_hdout.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Pre-processing and define learning function"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"FEATURES = [\"x1\", \"x2\", \"x3\"]\n",
"TARGET = [\"y\"]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"from fklearn.training.imputation import imputer\n",
"my_imputer = imputer(columns_to_impute=FEATURES, impute_strategy=\"median\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"from fklearn.training.transformation import standard_scaler\n",
"my_scaler = standard_scaler(columns_to_scale=FEATURES)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"from fklearn.training.regression import catboost_regressor_learner\n",
"my_model = catboost_regressor_learner(features=['x1', 'x2', 'x3'], target='y', prediction_column='prediction', extra_params={'random_seed': 139, 'thread_count': 8})"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"reload_all('fklearn')\n",
"# Learns an Empirical Cumulative Distribution Function from the specified column in the input DataFrame.\n",
"from fklearn.training.transformation import ecdfer \n",
"my_ecdefer = ecdfer(prediction_column=\"prediction\", ecdf_column=\"prediction_ecdf\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Building a pipeline"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"my_learner = build_pipeline(my_imputer, my_scaler, my_model, my_ecdefer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"(prediction_function, _, logs) = my_learner(train_set)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Evaluate"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"my_evaluator = combined_evaluators(evaluators=[\n",
" mean_prediction_evaluator(prediction_column='prediction'),\n",
" r2_evaluator(prediction_column='prediction', target_column='y'),\n",
" mse_evaluator(prediction_column='prediction', target_column='y'),\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"test_predictions = prediction_function(outime_outspace_hdout)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'mean_evaluator__prediction': 19093.91479387743,\n",
" 'r2_evaluator__y': 0.9958645292645391,\n",
" 'mse_evaluator__y': 335024.9617668662}"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_evaluator(test_predictions)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment