Revert "gQuant34 - Update build.sh to make use of RAPIDS v0.8 container"

NVIDIA · Aug 13, 2019 · ec8406b · ec8406b
1 parent 9c9cbe1
commit ec8406b
Show file tree

Hide file tree

Showing 5 changed files with 151 additions and 156 deletions.
diff --git a/build.sh b/build.sh
@@ -1,68 +1,65 @@
-#!/bin/bash
-
-echo "Building gQuant container..."
-
-read -p "Please, press '1' for cuda 9.2, or '2' for cuda 10.0. [1]/2: " CUDA_VERSION
-CUDA_VERSION=${CUDA_VERSION:-1}
-
-if [ "$CUDA_VERSION" -eq 2 ]; then
-    echo "cuda 10.0 selected."
-    CONTAINER='nvcr.io/nvidia/rapidsai/rapidsai:cuda10.0-runtime-ubuntu16.04'
-    CUPY='cupy-cuda100'
-else
-    echo "cuda 9.2 selected."
-    CONTAINER='nvcr.io/nvidia/rapidsai/rapidsai:cuda9.2-runtime-ubuntu16.04'
-    CUPY='cupy-cuda92'
-fi
-
-read -p "Would you like to install Vim JupyterLab Extension (optional) [N]/y: " VIM_INSTALL
-VIM_INSTALL=${VIM_INSTALL:-N}
-
-if [ "$VIM_INSTALL" = "Y" ] || [ "$VIM_INSTALL" = "y" ]; then
-    echo "Vim JupyterLab Extension will be installed."
-else
-    echo "Vim JupyterLab Extension will not be installed."
-fi
-
 D_FILE=${D_FILE:='Dockerfile.Rapids'}
 D_CONT=${D_CONT:='gquant/gquant:latest'}
 
-echo "Fetching latest version of gQuant project"
-git clone --recursive https://github.com/rapidsai/gQuant
-
-
 cat > $D_FILE <<EOF
-FROM $CONTAINER
-USER root
+FROM nvcr.io/nvidia/rapidsai/rapidsai:0.7-cuda10.0-devel-ubuntu18.04-gcc7-py3.6
 
-ADD gQuant /rapids/gQuant
+USER root
 
-RUN apt-get update && apt-get install -y libfontconfig1 libxrender1
+RUN apt-get update
+RUN apt-get install -y libfontconfig1 libxrender1
 
 SHELL ["bash","-c"]
-
 #
 # Additional python libs
 #
-RUN pip install nxpd graphviz pudb dask_labextension sphinx sphinx_rtd_theme recommonmark numpydoc $CUPY
-RUN conda install -y -c conda-forge python-graphviz bqplot=0.11.5 nodejs=11.11.0 jupyterlab=0.35.4 \
-    ipywidgets=7.4.2 pytables mkl numexpr
+RUN source activate rapids \
+    && pip install cython matplotlib networkx nxpd graphviz pudb
+
+RUN cd /rapids && source activate rapids \
+    && conda install -c conda-forge bqplot nodejs \
+    && conda install -y python-graphviz\
+    && conda install -y tqdm \
+    && conda install -y pytables \
+    && conda install -y -f mkl \
+    && conda install -y numpy scipy scikit-learn numexpr 
+    ## && conda install -c nvidia -c rapidsai -c numba -c conda-forge -c defaults cudf=0.6 python=3.6 cudatoolkit=10.0
+    ## && conda install -c rapidsai cudf \
+    ## && conda install -c rapidsai cuml \
+    ## && git clone https://github.com/rapidsai/cuml.git
 
 #
 # required set up
 #
-RUN jupyter labextension install @jupyter-widgets/[email protected] \
-    && jupyter labextension install [email protected] \
-    && mkdir /.local /.jupyter /.config /.cupy  \
-    && chmod 777 /.local /.jupyter /.config /.cupy
-
-RUN if [ "$VIM_INSTALL" = "Y" ] || [ "$VIM_INSTALL" = "y" ]; then /conda/envs/rapids/bin/jupyter labextension install [email protected] ; fi
+RUN source activate rapids \
+    && /conda/envs/rapids/bin/jupyter labextension install @jupyter-widgets/jupyterlab-manager \
+    && /conda/envs/rapids/bin/jupyter labextension install bqplot \
+    && mkdir /.local        \
+    && chmod 777 /.local    \
+    && mkdir /.jupyter      \
+    && chmod 777 /.jupyter  \
+    && mkdir /.config       \
+    && chmod 777 /.config   \
+    && mkdir /.cupy         \
+    && chmod 777 /.cupy
+
+RUN source activate rapids  \
+   && pip install dask_labextension \
+   && pip install sphinx sphinx_rtd_theme recommonmark numpydoc \
+   && /conda/envs/rapids/bin/jupyter labextension install dask-labextension \
+   && pip install cupy-cuda100
 
 EXPOSE 8888
 EXPOSE 8787
 EXPOSE 8786
 
+# the addon for vim editor
+# RUN source activate rapids  \
+#    && /conda/envs/rapids/bin/jupyter labextension install jupyterlab_vim
+
+
 WORKDIR /
 EOF
 
 docker build -f $D_FILE -t $D_CONT .
+
diff --git a/notebook/01_tutorial.ipynb b/notebook/01_tutorial.ipynb
diff --git a/notebook/02_single_stock_trade.ipynb b/notebook/02_single_stock_trade.ipynb
@@ -8,6 +8,13 @@
     "First import all the necessary modules."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -17,7 +24,6 @@
     "import sys\n",
     "sys.path.append('..')\n",
     "\n",
-    "import os\n",
     "import warnings\n",
     "import ipywidgets as widgets\n",
     "import nxpd\n",
@@ -192,7 +198,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c5f39b2436144ba594198a74d2743203",
+       "model_id": "69388a913ab54af9a4b2ea7bcce7e8ed",
        "version_major": 2,
        "version_minor": 0
       },
@@ -205,13 +211,11 @@
     }
    ],
    "source": [
-    "action = \"load\" if os.path.isfile('./.cache/node_csvdata.hdf5') else \"save\"\n",
-    "\n",
     "symbol = 'REXX'\n",
     "o = dff.run(obj,\n",
     "            outputs=['node_sharpeRatio', 'node_cumlativeReturn',\n",
     "                     'node_barplot', 'node_lineplot', 'node_csvdata'],\n",
-    "            replace={'node_csvdata': {action: True},\n",
+    "            replace={'node_csvdata': {\"load\": True},\n",
     "                     'node_barplot': {'conf': {\"points\": 300}},\n",
     "                     'node_assetFilter':\n",
     "                         {'conf': {'asset': list_stocks[symbol]}}})\n",
@@ -242,7 +246,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e0b9e4da549842e88078a6206ff8cc9e",
+       "model_id": "78618cf4870b49c2a29058e23cbe8fa6",
        "version_major": 2,
        "version_minor": 0
       },
@@ -274,7 +278,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "790208f8258c44b4a30b08552cd031bb",
+       "model_id": "d6e97f90036f4aacbb4e1998ae3e1515",
        "version_major": 2,
        "version_minor": 0
       },

diff --git a/notebook/03_simple_dask_example.ipynb b/notebook/03_simple_dask_example.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -27,7 +27,7 @@
        "<td style=\"vertical-align: top; border: 0px solid white\">\n",
        "<h3>Client</h3>\n",
        "<ul>\n",
-       "  <li><b>Scheduler: </b>tcp://127.0.0.1:37179\n",
+       "  <li><b>Scheduler: </b>tcp://127.0.0.1:38970\n",
        "  <li><b>Dashboard: </b><a href='http://127.0.0.1:8787/status' target='_blank'>http://127.0.0.1:8787/status</a>\n",
        "</ul>\n",
        "</td>\n",
@@ -36,17 +36,17 @@
        "<ul>\n",
        "  <li><b>Workers: </b>8</li>\n",
        "  <li><b>Cores: </b>8</li>\n",
-       "  <li><b>Memory: </b>540.95 GB</li>\n",
+       "  <li><b>Memory: </b>536.39 GB</li>\n",
        "</ul>\n",
        "</td>\n",
        "</tr>\n",
        "</table>"
       ],
       "text/plain": [
-       "<Client: scheduler='tcp://127.0.0.1:37179' processes=8 cores=8>"
+       "<Client: scheduler='tcp://127.0.0.1:38970' processes=8 cores=8>"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -68,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -89,7 +89,7 @@
        "<IPython.core.display.HTML object>"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -121,14 +121,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/conda/envs/rapids/lib/python3.6/site-packages/cudf/io/hdf.py:13: UserWarning: Using CPU via Pandas to read HDF dataset, this may be GPU accelerated in the future\n",
+      "/conda/envs/rapids/lib/python3.6/site-packages/cudf-0.7.1-py3.6-linux-x86_64.egg/cudf/io/hdf.py:13: UserWarning: Using CPU via Pandas to read HDF dataset, this may be GPU accelerated in the future\n",
       "  warnings.warn(\"Using CPU via Pandas to read HDF dataset, this may \"\n"
      ]
     },
@@ -156,18 +156,17 @@
     "import os\n",
     "node_csv = {\"id\": \"node_csvdata\",\n",
     "            \"type\": \"CsvStockLoader\",\n",
-    "            \"conf\": {\"path\": \"./data/stocks/stock_price_hist.csv.gz\"},\n",
+    "            \"conf\": {\"path\": \"/Project/data/stocks/stock_price_hist.csv.gz\"},\n",
     "            \"inputs\": []}\n",
     "\n",
     "node_sort = {\"id\": \"node_sort\",\n",
     "             \"type\": \"SortNode\",\n",
     "             \"conf\": {\"keys\": ['asset', 'datetime']},\n",
     "             \"inputs\": [\"node_csvdata\"]}\n",
     "\n",
-    "action = \"load\" if os.path.isfile('./.cache/node_csvdata.hdf5') else \"save\"\n",
     "df = run([node_csv, node_sort],\n",
     "         outputs=['node_sort'],\n",
-    "         replace={'node_csvdata': {action: True}})[0]\n",
+    "         replace={'node_csvdata': {\"load\": True}})[0]\n",
     "os.makedirs('many-small', exist_ok=True)\n",
     "print(df)\n",
     "df = dd.from_pandas(df.to_pandas(), npartitions=8).to_csv('many-small/*.csv', index=False)"