├── .DS_Store ├── .gitignore ├── .nojekyll ├── .travis.yml ├── LICENSE ├── MANIFEST.in ├── README.md ├── appveyor.yml ├── ci_scripts ├── .DS_Store ├── appveyor │ └── run_with_env.cmd ├── circleci │ └── push_doc.sh └── travis │ ├── install.sh │ ├── success.sh │ └── test.sh ├── circle.yml ├── doc ├── .DS_Store ├── Makefile ├── api.rst ├── classification.rst ├── classification │ ├── adaboost.rst │ ├── decision_tree.rst │ ├── extra_trees.rst │ ├── gbm.rst │ ├── linear_svm.rst │ ├── logistic_regression.rst │ ├── random_forest.rst │ └── sample.rst ├── conf.py ├── datablock.rst ├── feature_engineering.rst ├── index.rst ├── make.bat ├── modules │ └── .DS_Store └── preprocess.rst ├── easyML ├── .DS_Store ├── __init__.py ├── base_class.py ├── data.py ├── feature_engineering.py ├── genericmodelclass.py ├── models_classification.py ├── preprocess.py └── tests │ ├── .DS_Store │ ├── __init__.py │ ├── conftest.py │ ├── data_files │ ├── test.csv │ └── train.csv │ └── test_preprocess.py ├── examples └── README.txt ├── requirements.txt ├── requirements_dev.txt ├── setup.cfg └── setup.py /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # scikit-learn specific 10 | doc/_build/ 11 | doc/auto_examples/ 12 | doc/modules/generated/ 13 | doc/datasets/generated/ 14 | 15 | # Distribution / packaging 16 | 17 | .Python 18 | env/ 19 | build/ 20 | develop-eggs/ 21 | dist/ 22 | downloads/ 23 | eggs/ 24 | .eggs/ 25 | lib/ 26 | lib64/ 27 | parts/ 28 | sdist/ 29 | var/ 30 | *.egg-info/ 31 | .installed.cfg 32 | *.egg 33 | 34 | # PyInstaller 35 | # Usually these files are written by a python script from a template 36 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 37 | *.manifest 38 | *.spec 39 | 40 | # Installer logs 41 | pip-log.txt 42 | pip-delete-this-directory.txt 43 | 44 | # Unit test / coverage reports 45 | htmlcov/ 46 | .tox/ 47 | .coverage 48 | .coverage.* 49 | .cache 50 | nosetests.xml 51 | coverage.xml 52 | *,cover 53 | .hypothesis/ 54 | 55 | # Translations 56 | *.mo 57 | *.pot 58 | 59 | # Django stuff: 60 | *.log 61 | 62 | # Sphinx documentation 63 | docs/_build/ 64 | 65 | # PyBuilder 66 | target/ 67 | 68 | # Sublime Project: 69 | *.sublime-project 70 | *.sublime-workspace 71 | -------------------------------------------------------------------------------- /.nojekyll: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/.nojekyll -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: python 2 | python: 3 | - "2.7" 4 | - "3.5" 5 | 6 | install: 7 | - pip install -U pip 8 | - pip install numpy==1.12.0 scipy==0.18.1 9 | - pip install -r requirements_dev.txt 10 | script: pytest --pyarg easyML/tests/ -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Copyright (c) 2017, Aarshay Jain 2 | All rights reserved. 3 | 4 | Redistribution and use in source and binary forms, with or without 5 | modification, are permitted provided that the following conditions are met: 6 | 7 | * Redistributions of source code must retain the above copyright notice, this 8 | list of conditions and the following disclaimer. 9 | 10 | * Redistributions in binary form must reproduce the above copyright notice, 11 | this list of conditions and the following disclaimer in the documentation 12 | and/or other materials provided with the distribution. 13 | 14 | * Neither the name of easyML nor the names of its 15 | contributors may be used to endorse or promote products derived from 16 | this software without specific prior written permission. 17 | 18 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 19 | AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 20 | IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 21 | DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE 22 | FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 23 | DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR 24 | SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 25 | CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, 26 | OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 27 | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 28 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include requirements.txt 2 | include requirements_dev.txt 3 | include README.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | #easyML - Code Less, Do More!! 2 | 3 | [![Travis Status](https://travis-ci.org/aarshayj/easyML.svg?branch=master)](https://travis-ci.org/aarshayj/easyML) 4 | [![CircleCI Status](https://circleci.com/gh/aarshayj/easyML.svg?style=shield&circle-token=:circle-token)](https://circleci.com/gh/aarshayj/easyML/tree/master) 5 | [![PyPi Version](https://badge.fury.io/py/easyML.svg)](https://pypi.python.org/pypi/easyML/0.1.0) 6 | 7 | **easyML** is a python package designed to streamline the process of analyzing datasets using predictive models. It covers crutial aspects the of data analysis process starting from preprocessing, to feature engineering and finally predictive modeling. 8 | 9 | They key advantage of this package is the DataBlock module using which you can create a block of your data at the start of analysis. The other modules take this block as input and seemlessly work on your data together. It definitely comes at the cost of loss of generalization as compared to the raw scikit-learn features, but the idea is to incorporate typically used actions and also provide options for flexibility through user-defined tasks. The package is particularly useful for begineers and intermediate level python data science enthusiasts, who are looking to get the job done without worrying about the code. 10 | 11 | ## Important Links 12 | * [HTML Documentation](https://aarshayj.github.io/easyML/) 13 | * [PyPi](https://pypi.python.org/pypi/easyML/0.1.0) 14 | * Examples - Coming soon! 15 | 16 | ## Installation and Usage 17 | The module can be installed using Github or PyPi as: 18 | ``` 19 | pip install easyML 20 | ``` 21 | 22 | ## Motivation - How it all began? 23 | 24 | I would like to share my motivation behind making this package. I started my data science career using R and SAS but then decided to switch to Python about a year and a half back. I started with the scikit-learn package and I was taken aback by the amount of coding required. In R, when you build a model in caret, it gives you a lot of information required to analyze them. But here, everything has to be coded separately. After some struggle, I decided to create wrapper functions for myself which allowed me to re-use most of the code that I wrote and not worry about looking for syntaxes every time I start a new analysis. My library developed over time. 25 | 26 | Then I joined the MS in Data Science program at Columbia and got busy with academics. Returning to Python after a break of ~6 months, my library came in very handy when I had to do a quick project as I had forgotten most of the syntaxes. Doing everything from scratch would have been a nightmare. Its then that I realized that if its so useful for me, I should open-source my work. This is just the beginning, there's lots more to come. 27 | 28 | ## How can you contribute? 29 | 30 | What you see now is an alpha-version of the package. I have defined a framework with a class structure having clear dataflow. The module contains some fundamental modules. There's still a lot to be done as there are lots of cool modules to be added. I have my upcoming functions list in each module. 31 | 32 | I'm sure if you are a serious analyst/data scientist, you would have many such wrappers of your own. I would love to hear about them and it'll be great if you contrinute your ideas/code. Even if you don't have the code, feel free to add feature requests for things you would like see. 33 | -------------------------------------------------------------------------------- /appveyor.yml: -------------------------------------------------------------------------------- 1 | # AppVeyor.com is a Continuous Integration service to build and run tests under 2 | # Windows 3 | 4 | 5 | environment: 6 | global: 7 | # SDK v7.0 MSVC Express 2008's SetEnv.cmd script will fail if the 8 | # /E:ON and /V:ON options are not enabled in the batch script interpreter 9 | # See: http://stackoverflow.com/a/13751649/163740 10 | CMD_IN_ENV: "cmd /E:ON /V:ON /C .\\ci_scripts\\appveyor\\run_with_env.cmd" 11 | WHEELHOUSE_UPLOADER_USERNAME: sklearn 12 | WHEELHOUSE_UPLOADER_SECRET: 13 | secure: XzK+Mi6Ba5frV2B/jHq7h4aD8/nox9SsI3T8Kub1L2XNevRSIurUEry3PdWESzRY 14 | MODULE: skltemplate 15 | PROJECT_NAME: sklearn-template 16 | CLOUD_STORAGE: CLOUDFILES 17 | CLOUD_CONTATINER: sklearn-template-trial 18 | 19 | matrix: 20 | - PYTHON: "C:\\Python27" 21 | PYTHON_VERSION: "2.7.8" 22 | PYTHON_ARCH: "32" 23 | MINICONDA: "C:\\Miniconda" 24 | 25 | - PYTHON: "C:\\Python27-x64" 26 | PYTHON_VERSION: "2.7.8" 27 | PYTHON_ARCH: "64" 28 | MINICONDA: "C:\\Miniconda-x64" 29 | 30 | - PYTHON: "C:\\Python35" 31 | PYTHON_VERSION: "3.5.0" 32 | PYTHON_ARCH: "32" 33 | MINICONDA: "C:\\Miniconda35" 34 | 35 | - PYTHON: "C:\\Python35-x64" 36 | PYTHON_VERSION: "3.5.0" 37 | PYTHON_ARCH: "64" 38 | MINICONDA: "C:\\Miniconda35-x64" 39 | 40 | install: 41 | # Miniconda is pre-installed in the worker build 42 | - "SET PATH=%MINICONDA%;%MINICONDA%\\Scripts;%PATH%" 43 | - "python -m pip install -U pip" 44 | 45 | # Check that we have the expected version and architecture for Python 46 | - "python --version" 47 | - "python -c \"import struct; print(struct.calcsize('P') * 8)\"" 48 | - "pip --version" 49 | 50 | # Remove cygwin because it clashes with conda 51 | # see http://help.appveyor.com/discussions/problems/3712-git-remote-https-seems-to-be-broken 52 | - rmdir C:\\cygwin /s /q 53 | 54 | # Install the build and runtime dependencies of the project. 55 | - conda install --quiet --yes numpy scipy cython nose scikit-learn wheel 56 | - pip install wheelhouse_uploader nose-timer 57 | - "%CMD_IN_ENV% python setup.py bdist_wheel bdist_wininst" 58 | - ps: "ls dist" 59 | 60 | # Install the generated wheel package to test it 61 | - "pip install --pre --no-index --find-links dist %PROJECT_NAME%" 62 | 63 | 64 | # Not a .NET project, we build scikit-learn in the install step instead 65 | build: false 66 | 67 | 68 | artifacts: 69 | # Archive the generated wheel package in the ci.appveyor.com build report. 70 | - path: dist\* 71 | 72 | 73 | on_success: 74 | # Upload the generated wheel package to Rackspace 75 | # On Windows, Apache Libcloud cannot find a standard CA cert bundle so we 76 | # disable the ssl checks. 77 | - "python -m wheelhouse_uploader upload provider=%CLOUD_STORAGE% --no-ssl-check --local-folder=dist %CLOUD_CONTAINER%" 78 | 79 | 80 | test_script: 81 | # Change to a non-source folder to make sure we run the tests on the 82 | # installed library. 83 | - "mkdir empty_folder" 84 | - "cd empty_folder" 85 | 86 | - "python -c \"import nose; nose.main()\" --with-timer --timer-top-n 20 -s -v %MODULE%" 87 | 88 | # Move back to the project folder 89 | - "cd .." 90 | 91 | 92 | cache: 93 | # Use the appveyor cache to avoid re-downloading large archives such 94 | # the MKL numpy and scipy wheels mirrored on a rackspace cloud 95 | # container, speed up the appveyor jobs and reduce bandwidth 96 | # usage on our rackspace account. 97 | - '%APPDATA%\pip\Cache' -------------------------------------------------------------------------------- /ci_scripts/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/ci_scripts/.DS_Store -------------------------------------------------------------------------------- /ci_scripts/appveyor/run_with_env.cmd: -------------------------------------------------------------------------------- 1 | :: To build extensions for 64 bit Python 3, we need to configure environment 2 | :: variables to use the MSVC 2010 C++ compilers from GRMSDKX_EN_DVD.iso of: 3 | :: MS Windows SDK for Windows 7 and .NET Framework 4 (SDK v7.1) 4 | :: 5 | :: To build extensions for 64 bit Python 2, we need to configure environment 6 | :: variables to use the MSVC 2008 C++ compilers from GRMSDKX_EN_DVD.iso of: 7 | :: MS Windows SDK for Windows 7 and .NET Framework 3.5 (SDK v7.0) 8 | :: 9 | :: 32 bit builds, and 64-bit builds for 3.5 and beyond, do not require specific 10 | :: environment configurations. 11 | :: 12 | :: Note: this script needs to be run with the /E:ON and /V:ON flags for the 13 | :: cmd interpreter, at least for (SDK v7.0) 14 | :: 15 | :: More details at: 16 | :: https://github.com/cython/cython/wiki/64BitCythonExtensionsOnWindows 17 | :: http://stackoverflow.com/a/13751649/163740 18 | :: 19 | :: Author: Olivier Grisel 20 | :: License: CC0 1.0 Universal: http://creativecommons.org/publicdomain/zero/1.0/ 21 | :: 22 | :: Notes about batch files for Python people: 23 | :: 24 | :: Quotes in values are literally part of the values: 25 | :: SET FOO="bar" 26 | :: FOO is now five characters long: " b a r " 27 | :: If you don't want quotes, don't include them on the right-hand side. 28 | :: 29 | :: The CALL lines at the end of this file look redundant, but if you move them 30 | :: outside of the IF clauses, they do not run properly in the SET_SDK_64==Y 31 | :: case, I don't know why. 32 | @ECHO OFF 33 | 34 | SET COMMAND_TO_RUN=%* 35 | SET WIN_SDK_ROOT=C:\Program Files\Microsoft SDKs\Windows 36 | SET WIN_WDK=c:\Program Files (x86)\Windows Kits\10\Include\wdf 37 | 38 | :: Extract the major and minor versions, and allow for the minor version to be 39 | :: more than 9. This requires the version number to have two dots in it. 40 | SET MAJOR_PYTHON_VERSION=%PYTHON_VERSION:~0,1% 41 | IF "%PYTHON_VERSION:~3,1%" == "." ( 42 | SET MINOR_PYTHON_VERSION=%PYTHON_VERSION:~2,1% 43 | ) ELSE ( 44 | SET MINOR_PYTHON_VERSION=%PYTHON_VERSION:~2,2% 45 | ) 46 | 47 | :: Based on the Python version, determine what SDK version to use, and whether 48 | :: to set the SDK for 64-bit. 49 | IF %MAJOR_PYTHON_VERSION% == 2 ( 50 | SET WINDOWS_SDK_VERSION="v7.0" 51 | SET SET_SDK_64=Y 52 | ) ELSE ( 53 | IF %MAJOR_PYTHON_VERSION% == 3 ( 54 | SET WINDOWS_SDK_VERSION="v7.1" 55 | IF %MINOR_PYTHON_VERSION% LEQ 4 ( 56 | SET SET_SDK_64=Y 57 | ) ELSE ( 58 | SET SET_SDK_64=N 59 | IF EXIST "%WIN_WDK%" ( 60 | :: See: https://connect.microsoft.com/VisualStudio/feedback/details/1610302/ 61 | REN "%WIN_WDK%" 0wdf 62 | ) 63 | ) 64 | ) ELSE ( 65 | ECHO Unsupported Python version: "%MAJOR_PYTHON_VERSION%" 66 | EXIT 1 67 | ) 68 | ) 69 | 70 | IF %PYTHON_ARCH% == 64 ( 71 | IF %SET_SDK_64% == Y ( 72 | ECHO Configuring Windows SDK %WINDOWS_SDK_VERSION% for Python %MAJOR_PYTHON_VERSION% on a 64 bit architecture 73 | SET DISTUTILS_USE_SDK=1 74 | SET MSSdk=1 75 | "%WIN_SDK_ROOT%\%WINDOWS_SDK_VERSION%\Setup\WindowsSdkVer.exe" -q -version:%WINDOWS_SDK_VERSION% 76 | "%WIN_SDK_ROOT%\%WINDOWS_SDK_VERSION%\Bin\SetEnv.cmd" /x64 /release 77 | ECHO Executing: %COMMAND_TO_RUN% 78 | call %COMMAND_TO_RUN% || EXIT 1 79 | ) ELSE ( 80 | ECHO Using default MSVC build environment for 64 bit architecture 81 | ECHO Executing: %COMMAND_TO_RUN% 82 | call %COMMAND_TO_RUN% || EXIT 1 83 | ) 84 | ) ELSE ( 85 | ECHO Using default MSVC build environment for 32 bit architecture 86 | ECHO Executing: %COMMAND_TO_RUN% 87 | call %COMMAND_TO_RUN% || EXIT 1 88 | ) 89 | -------------------------------------------------------------------------------- /ci_scripts/circleci/push_doc.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # This script is meant to be called in the "deploy" step defined in 3 | # circle.yml. See https://circleci.com/docs/ for more details. 4 | # The behavior of the script is controlled by environment variable defined 5 | # in the circle.yml in the top level folder of the project. 6 | 7 | MSG="Pushing the docs for revision for branch: $CIRCLE_BRANCH, commit $CIRCLE_SHA1" 8 | 9 | cd $HOME 10 | # Copy the build docs to a temporary folder 11 | rm -rf tmp 12 | mkdir tmp 13 | cp -R $HOME/$DOC_REPO/doc/_build/html/* ./tmp/ 14 | 15 | # Clone the docs repo if it isnt already there 16 | if [ ! -d $DOC_REPO ]; 17 | then git clone "git@github.com:$USERNAME/"$DOC_REPO".git"; 18 | fi 19 | 20 | cd $DOC_REPO 21 | git branch gh-pages 22 | git checkout -f gh-pages 23 | git reset --hard origin/gh-pages 24 | git clean -dfx 25 | 26 | for name in $(ls -A $HOME/$DOC_REPO); do 27 | case $name in 28 | .nojekyll) # So that github does not build this as a Jekyll website. 29 | ;; 30 | circle.yml) # Config so that build gh-pages branch. 31 | ;; 32 | *) 33 | git rm -rf $name 34 | ;; 35 | esac 36 | done 37 | 38 | # Copy the new build docs 39 | mkdir $DOC_URL 40 | cp -R $HOME/tmp/* ./$DOC_URL/ 41 | 42 | git config --global user.email $EMAIL 43 | git config --global user.name $USERNAME 44 | git add -f ./$DOC_URL/ 45 | git commit -m "$MSG" 46 | git push -f origin gh-pages 47 | if [ $? -ne 0 ]; then 48 | echo "Pushing docs failed" 49 | echo 50 | exit 1 51 | fi 52 | 53 | echo $MSG 54 | -------------------------------------------------------------------------------- /ci_scripts/travis/install.sh: -------------------------------------------------------------------------------- 1 | # Deactivate the travis-provided virtual environment and setup a 2 | # conda-based environment instead 3 | deactivate 4 | 5 | # Use the miniconda installer for faster download / install of conda 6 | # itself 7 | pushd . 8 | cd 9 | mkdir -p download 10 | cd download 11 | echo "Cached in $HOME/download :" 12 | ls -l 13 | echo 14 | if [[ ! -f miniconda.sh ]] 15 | then 16 | wget http://repo.continuum.io/miniconda/Miniconda-3.6.0-Linux-x86_64.sh \ 17 | -O miniconda.sh 18 | fi 19 | chmod +x miniconda.sh && ./miniconda.sh -b 20 | cd .. 21 | export PATH=/home/travis/miniconda/bin:$PATH 22 | conda update --yes conda 23 | popd 24 | 25 | # Configure the conda environment and put it in the path using the 26 | # provided versions 27 | conda create -n testenv --yes python=$PYTHON_VERSION pip pytest \ 28 | numpy=$NUMPY_VERSION scipy=$SCIPY_VERSION cython=$CYTHON_VERSION 29 | 30 | source activate testenv 31 | 32 | if [[ "$COVERAGE" == "true" ]]; then 33 | pip install coverage coveralls 34 | fi 35 | 36 | python --version 37 | python -c "import numpy; print('numpy %s' % numpy.__version__)" 38 | python -c "import scipy; print('scipy %s' % scipy.__version__)" 39 | python setup.py develop 40 | -------------------------------------------------------------------------------- /ci_scripts/travis/success.sh: -------------------------------------------------------------------------------- 1 | set -e 2 | 3 | if [[ "$COVERAGE" == "true" ]]; then 4 | # Need to run coveralls from a git checkout, so we copy .coverage 5 | # from TEST_DIR where pytests has been run 6 | cp $TEST_DIR/.coverage $TRAVIS_BUILD_DIR 7 | cd $TRAVIS_BUILD_DIR 8 | # Ignore coveralls failures as the coveralls server is not 9 | # very reliable but we don't want travis to report a failure 10 | # in the github UI just because the coverage report failed to 11 | # be published. 12 | coveralls || echo "Coveralls upload failed" 13 | fi -------------------------------------------------------------------------------- /ci_scripts/travis/test.sh: -------------------------------------------------------------------------------- 1 | set -e 2 | 3 | # Get into a temp directory to run test from the installed scikit learn and 4 | # check if we do not leave artifacts 5 | mkdir -p $TEST_DIR 6 | 7 | cd $TEST_DIR 8 | 9 | if [[ "$COVERAGE" == "true" ]]; then 10 | py.test --cov=$MODULE --pyargs $MODULE 11 | else 12 | py.test --pyargs $MODULE 13 | fi 14 | -------------------------------------------------------------------------------- /circle.yml: -------------------------------------------------------------------------------- 1 | machine: 2 | environment: 3 | # The github organization or username of the repository which hosts the 4 | # project and documentation. 5 | USERNAME: "aarshayj" 6 | 7 | # The repository where the documentation will be hosted 8 | DOC_REPO: "easyML" 9 | 10 | # The base URL for the Github page where the documentation will be hosted 11 | DOC_URL: "" 12 | 13 | # The email is to be used for commits in the Github Page 14 | EMAIL: "aarshay.jain@columbia.edu" 15 | 16 | dependencies: 17 | 18 | # Various dependencies 19 | pre: 20 | - sudo -E apt-get -yq remove texlive-binaries --purge 21 | - sudo apt-get update 22 | - sudo apt-get install libatlas-dev libatlas3gf-base 23 | - sudo apt-get install build-essential python-dev python-setuptools 24 | # install numpy first as it is a compile time dependency for other packages 25 | - pip install --upgrade numpy 26 | - pip install --upgrade scipy matplotlib setuptools nose coverage sphinx pillow sphinx-gallery sphinx_rtd_theme 27 | # Installing required packages for `make -C doc check command` to work. 28 | - sudo -E apt-get -yq update 29 | - sudo -E apt-get -yq --no-install-suggests --no-install-recommends --force-yes install dvipng texlive-latex-base texlive-latex-extra 30 | - pip install --upgrade cython numpydoc 31 | - pip install --upgrade scikit-learn 32 | 33 | # The --user is needed to let sphinx see the source and the binaries 34 | # The pipefail is requested to propagate exit code 35 | override: 36 | - python setup.py clean 37 | - python setup.py develop 38 | - set -o pipefail && cd doc && make html 2>&1 | tee ~/log.txt 39 | test: 40 | # Grep error on the documentation 41 | override: 42 | - cat ~/log.txt && if grep -q "Traceback (most recent call last):" ~/log.txt; then false; else true; fi 43 | deployment: 44 | push: 45 | branch: master 46 | commands: 47 | - bash ci_scripts/circleci/push_doc.sh 48 | general: 49 | # Open the doc to the API 50 | artifacts: 51 | - "doc/_build/html" 52 | - "~/log.txt" 53 | # Restric the build to the branch master only 54 | branches: 55 | ignore: 56 | - gh-pages -------------------------------------------------------------------------------- /doc/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/doc/.DS_Store -------------------------------------------------------------------------------- /doc/Makefile: -------------------------------------------------------------------------------- 1 | # Makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line. 5 | SPHINXOPTS = 6 | SPHINXBUILD = sphinx-build 7 | PAPER = 8 | BUILDDIR = _build 9 | 10 | # User-friendly check for sphinx-build 11 | ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1) 12 | $(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/) 13 | endif 14 | 15 | # Internal variables. 16 | PAPEROPT_a4 = -D latex_paper_size=a4 17 | PAPEROPT_letter = -D latex_paper_size=letter 18 | ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . 19 | # the i18n builder cannot share the environment and doctrees with the others 20 | I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . 21 | 22 | .PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext 23 | 24 | help: 25 | @echo "Please use \`make ' where is one of" 26 | @echo " html to make standalone HTML files" 27 | @echo " dirhtml to make HTML files named index.html in directories" 28 | @echo " singlehtml to make a single large HTML file" 29 | @echo " pickle to make pickle files" 30 | @echo " json to make JSON files" 31 | @echo " htmlhelp to make HTML files and a HTML help project" 32 | @echo " qthelp to make HTML files and a qthelp project" 33 | @echo " devhelp to make HTML files and a Devhelp project" 34 | @echo " epub to make an epub" 35 | @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" 36 | @echo " latexpdf to make LaTeX files and run them through pdflatex" 37 | @echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx" 38 | @echo " text to make text files" 39 | @echo " man to make manual pages" 40 | @echo " texinfo to make Texinfo files" 41 | @echo " info to make Texinfo files and run them through makeinfo" 42 | @echo " gettext to make PO message catalogs" 43 | @echo " changes to make an overview of all changed/added/deprecated items" 44 | @echo " xml to make Docutils-native XML files" 45 | @echo " pseudoxml to make pseudoxml-XML files for display purposes" 46 | @echo " linkcheck to check all external links for integrity" 47 | @echo " doctest to run all doctests embedded in the documentation (if enabled)" 48 | 49 | clean: 50 | -rm -rf $(BUILDDIR)/* 51 | -rm -rf auto_examples/ 52 | -rm -rf generated/* 53 | -rm -rf modules/generated/* 54 | 55 | html: 56 | # These two lines make the build a bit more lengthy, and the 57 | # the embedding of images more robust 58 | rm -rf $(BUILDDIR)/html/_images 59 | #rm -rf _build/doctrees/ 60 | $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html 61 | @echo 62 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." 63 | 64 | dirhtml: 65 | $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml 66 | @echo 67 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." 68 | 69 | singlehtml: 70 | $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml 71 | @echo 72 | @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." 73 | 74 | pickle: 75 | $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle 76 | @echo 77 | @echo "Build finished; now you can process the pickle files." 78 | 79 | json: 80 | $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json 81 | @echo 82 | @echo "Build finished; now you can process the JSON files." 83 | 84 | htmlhelp: 85 | $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp 86 | @echo 87 | @echo "Build finished; now you can run HTML Help Workshop with the" \ 88 | ".hhp project file in $(BUILDDIR)/htmlhelp." 89 | 90 | qthelp: 91 | $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp 92 | @echo 93 | @echo "Build finished; now you can run "qcollectiongenerator" with the" \ 94 | ".qhcp project file in $(BUILDDIR)/qthelp, like this:" 95 | @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/project-template.qhcp" 96 | @echo "To view the help file:" 97 | @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/project-template.qhc" 98 | 99 | devhelp: 100 | $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp 101 | @echo 102 | @echo "Build finished." 103 | @echo "To view the help file:" 104 | @echo "# mkdir -p $$HOME/.local/share/devhelp/project-template" 105 | @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/project-template" 106 | @echo "# devhelp" 107 | 108 | epub: 109 | $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub 110 | @echo 111 | @echo "Build finished. The epub file is in $(BUILDDIR)/epub." 112 | 113 | latex: 114 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 115 | @echo 116 | @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." 117 | @echo "Run \`make' in that directory to run these through (pdf)latex" \ 118 | "(use \`make latexpdf' here to do that automatically)." 119 | 120 | latexpdf: 121 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 122 | @echo "Running LaTeX files through pdflatex..." 123 | $(MAKE) -C $(BUILDDIR)/latex all-pdf 124 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." 125 | 126 | latexpdfja: 127 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 128 | @echo "Running LaTeX files through platex and dvipdfmx..." 129 | $(MAKE) -C $(BUILDDIR)/latex all-pdf-ja 130 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." 131 | 132 | text: 133 | $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text 134 | @echo 135 | @echo "Build finished. The text files are in $(BUILDDIR)/text." 136 | 137 | man: 138 | $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man 139 | @echo 140 | @echo "Build finished. The manual pages are in $(BUILDDIR)/man." 141 | 142 | texinfo: 143 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo 144 | @echo 145 | @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." 146 | @echo "Run \`make' in that directory to run these through makeinfo" \ 147 | "(use \`make info' here to do that automatically)." 148 | 149 | info: 150 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo 151 | @echo "Running Texinfo files through makeinfo..." 152 | make -C $(BUILDDIR)/texinfo info 153 | @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." 154 | 155 | gettext: 156 | $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale 157 | @echo 158 | @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." 159 | 160 | changes: 161 | $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes 162 | @echo 163 | @echo "The overview file is in $(BUILDDIR)/changes." 164 | 165 | linkcheck: 166 | $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck 167 | @echo 168 | @echo "Link check complete; look for any errors in the above output " \ 169 | "or in $(BUILDDIR)/linkcheck/output.txt." 170 | 171 | doctest: 172 | $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest 173 | @echo "Testing of doctests in the sources finished, look at the " \ 174 | "results in $(BUILDDIR)/doctest/output.txt." 175 | 176 | xml: 177 | $(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml 178 | @echo 179 | @echo "Build finished. The XML files are in $(BUILDDIR)/xml." 180 | 181 | pseudoxml: 182 | $(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml 183 | @echo 184 | @echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml." 185 | -------------------------------------------------------------------------------- /doc/api.rst: -------------------------------------------------------------------------------- 1 | API Documentation 2 | ================= 3 | 4 | .. toctree:: 5 | :maxdepth: 3 6 | 7 | datablock 8 | preprocess 9 | feature_engineering 10 | classification 11 | 12 | Notes 13 | ----------------- 14 | 15 | - The package supports some features in preprocess and feature engineering modules. Others will be added soon. 16 | - The package has only classification algorithms for now and regression models will be added after some testing on classification part. 17 | - The package is still in alpha-development stage and test cases are being added regularly. If you find bugs, please report them using GitHub. -------------------------------------------------------------------------------- /doc/classification.rst: -------------------------------------------------------------------------------- 1 | Classification Models 2 | ===================== 3 | 4 | This module helps you perform the classification task using a variety of models from scikit-learn implementation. This module provides an easy to use interface with following advantages: 5 | 6 | - Define scoring metrics at time of initialization, which gets computed at time of modelfit 7 | - A single line of code allows you to: 8 | + Fit the model 9 | + Compute pre-defined scoring metrics on both test and train data 10 | + Make predictions on data with unknown labels 11 | + Print a summary of the model with pre-defined metrics and feature importance charts 12 | - Perform easy grid search 13 | - Perform recursive feature elimination 14 | 15 | Supported Algorithms 16 | -------------------- 17 | 18 | The module supports a bunch of scikit-learn's modules as below: 19 | 20 | .. toctree:: 21 | :maxdepth: 3 22 | 23 | classification/logistic_regression 24 | classification/decision_tree 25 | classification/random_forest 26 | classification/extra_trees 27 | classification/adaboost 28 | classification/gbm 29 | classification/linear_svm 30 | 31 | Note: The support for XGBoost is coming up next. Stay tuned!! 32 | -------------------------------------------------------------------------------- /doc/classification/adaboost.rst: -------------------------------------------------------------------------------- 1 | Adaboost (Classifier) 2 | --------------------------- 3 | 4 | .. autoclass:: easyML.models_classification.adaboost 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | 7 | -------------------------------------------------------------------------------- /doc/classification/decision_tree.rst: -------------------------------------------------------------------------------- 1 | Decision Tree (Classifier) 2 | -------------------------- 3 | 4 | .. autoclass:: easyML.models_classification.decision_tree 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | -------------------------------------------------------------------------------- /doc/classification/extra_trees.rst: -------------------------------------------------------------------------------- 1 | Extra Trees Forest (Classifier) 2 | -------------------------------- 3 | 4 | .. autoclass:: easyML.models_classification.extra_trees 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | 7 | -------------------------------------------------------------------------------- /doc/classification/gbm.rst: -------------------------------------------------------------------------------- 1 | Gradient Boosting Machine (Classifier) 2 | -------------------------------------- 3 | 4 | .. autoclass:: easyML.models_classification.gradient_boosting_machine 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | 7 | -------------------------------------------------------------------------------- /doc/classification/linear_svm.rst: -------------------------------------------------------------------------------- 1 | Linear Support Vector Machine (Classifier) 2 | ------------------------------------------ 3 | 4 | .. autoclass:: easyML.models_classification. 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | -------------------------------------------------------------------------------- /doc/classification/logistic_regression.rst: -------------------------------------------------------------------------------- 1 | Logistic Regression 2 | ------------------- 3 | 4 | .. autoclass:: easyML.models_classification.logistic_regression 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | -------------------------------------------------------------------------------- /doc/classification/random_forest.rst: -------------------------------------------------------------------------------- 1 | Random Forest (Classifier) 2 | --------------------------- 3 | 4 | .. autoclass:: easyML.models_classification.random_forest 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | 7 | -------------------------------------------------------------------------------- /doc/classification/sample.rst: -------------------------------------------------------------------------------- 1 | 2 | --------------------------- 3 | 4 | .. autoclass:: easyML.models_classification. 5 | :inherited-members: set_predictors, set_scoring_metric, recursive_feature_elimination, recursive_feature_elimination_cv, grid_search, submission, fit_model, submission_proba, set_parameters, export_model 6 | -------------------------------------------------------------------------------- /doc/conf.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # 3 | # project-template documentation build configuration file, created by 4 | # sphinx-quickstart on Mon Jan 18 14:44:12 2016. 5 | # 6 | # This file is execfile()d with the current directory set to its 7 | # containing dir. 8 | # 9 | # Note that not all possible configuration values are present in this 10 | # autogenerated file. 11 | # 12 | # All configuration values have a default; values that are commented out 13 | # serve to show the default. 14 | 15 | import sys 16 | import os 17 | 18 | import sphinx_rtd_theme 19 | 20 | # If extensions (or modules to document with autodoc) are in another directory, 21 | # add these directories to sys.path here. If the directory is relative to the 22 | # documentation root, use os.path.abspath to make it absolute, like shown here. 23 | sys.path.insert(0, os.path.abspath('..')) 24 | 25 | # -- General configuration --------------------------------------------------- 26 | 27 | # Try to override the matplotlib configuration as early as possible 28 | try: 29 | import gen_rst 30 | except: 31 | pass 32 | # -- General configuration ------------------------------------------------ 33 | 34 | # If your documentation needs a minimal Sphinx version, state it here. 35 | #needs_sphinx = '1.0' 36 | 37 | # Add any Sphinx extension module names here, as strings. They can be 38 | # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom 39 | # ones. 40 | extensions = [ 41 | 'sphinx.ext.autodoc', 42 | 'sphinx.ext.doctest', 43 | 'sphinx.ext.intersphinx', 44 | 'sphinx.ext.todo', 45 | 'numpydoc', 46 | 'sphinx.ext.ifconfig', 47 | 'sphinx.ext.viewcode', 48 | 'sphinx_gallery.gen_gallery' 49 | 50 | ] 51 | 52 | # pngmath / imgmath compatibility layer for different sphinx versions 53 | import sphinx 54 | from distutils.version import LooseVersion 55 | if LooseVersion(sphinx.__version__) < LooseVersion('1.4'): 56 | extensions.append('sphinx.ext.pngmath') 57 | else: 58 | extensions.append('sphinx.ext.imgmath') 59 | 60 | sphinx_gallery_conf = { 61 | # path to your examples scripts 62 | 'examples_dirs' : '../examples', 63 | # path where to save gallery generated examples 64 | 'gallery_dirs' : 'auto_examples'} 65 | 66 | # Add any paths that contain templates here, relative to this directory. 67 | templates_path = ['_templates'] 68 | 69 | # The suffix of source filenames. 70 | source_suffix = '.rst' 71 | 72 | # The encoding of source files. 73 | #source_encoding = 'utf-8-sig' 74 | 75 | # Generate the plots for the gallery 76 | plot_gallery = True 77 | 78 | # The master toctree document. 79 | master_doc = 'index' 80 | 81 | # General information about the project. 82 | project = u'easyML' 83 | copyright = u'2017, Aarshay Jain' 84 | 85 | # The version info for the project you're documenting, acts as replacement for 86 | # |version| and |release|, also used in various other places throughout the 87 | # built documents. 88 | # 89 | # The short X.Y version. 90 | version = '0.1' 91 | # The full version, including alpha/beta/rc tags. 92 | release = '0.1.0al' 93 | 94 | # The language for content autogenerated by Sphinx. Refer to documentation 95 | # for a list of supported languages. 96 | #language = None 97 | 98 | # There are two options for replacing |today|: either, you set today to some 99 | # non-false value, then it is used: 100 | #today = '' 101 | # Else, today_fmt is used as the format for a strftime call. 102 | #today_fmt = '%B %d, %Y' 103 | 104 | # List of patterns, relative to source directory, that match files and 105 | # directories to ignore when looking for source files. 106 | exclude_patterns = ['_build'] 107 | 108 | # The reST default role (used for this markup: `text`) to use for all 109 | # documents. 110 | #default_role = None 111 | 112 | # If true, '()' will be appended to :func: etc. cross-reference text. 113 | #add_function_parentheses = True 114 | 115 | # If true, the current module name will be prepended to all description 116 | # unit titles (such as .. function::). 117 | #add_module_names = True 118 | 119 | # If true, sectionauthor and moduleauthor directives will be shown in the 120 | # output. They are ignored by default. 121 | #show_authors = False 122 | 123 | # The name of the Pygments (syntax highlighting) style to use. 124 | pygments_style = 'sphinx' 125 | 126 | # A list of ignored prefixes for module index sorting. 127 | #modindex_common_prefix = [] 128 | 129 | # If true, keep warnings as "system message" paragraphs in the built documents. 130 | #keep_warnings = False 131 | 132 | 133 | # -- Options for HTML output ---------------------------------------------- 134 | 135 | # The theme to use for HTML and HTML Help pages. See the documentation for 136 | # a list of builtin themes. 137 | html_theme = 'sphinx_rtd_theme' 138 | 139 | # Theme options are theme-specific and customize the look and feel of a theme 140 | # further. For a list of options available for each theme, see the 141 | # documentation. 142 | #html_theme_options = {} 143 | 144 | # Add any paths that contain custom themes here, relative to this directory. 145 | html_theme_path = [sphinx_rtd_theme.get_html_theme_path()] 146 | 147 | # The name for this set of Sphinx documents. If None, it defaults to 148 | # " v documentation". 149 | #html_title = None 150 | 151 | # A shorter title for the navigation bar. Default is the same as html_title. 152 | #html_short_title = None 153 | 154 | # The name of an image file (relative to this directory) to place at the top 155 | # of the sidebar. 156 | #html_logo = None 157 | 158 | # The name of an image file (within the static path) to use as favicon of the 159 | # docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 160 | # pixels large. 161 | #html_favicon = None 162 | 163 | # Add any paths that contain custom static files (such as style sheets) here, 164 | # relative to this directory. They are copied after the builtin static files, 165 | # so a file named "default.css" will overwrite the builtin "default.css". 166 | html_static_path = ['_static'] 167 | 168 | # Add any extra paths that contain custom files (such as robots.txt or 169 | # .htaccess) here, relative to this directory. These files are copied 170 | # directly to the root of the documentation. 171 | #html_extra_path = [] 172 | 173 | # If not '', a 'Last updated on:' timestamp is inserted at every page bottom, 174 | # using the given strftime format. 175 | #html_last_updated_fmt = '%b %d, %Y' 176 | 177 | # If true, SmartyPants will be used to convert quotes and dashes to 178 | # typographically correct entities. 179 | #html_use_smartypants = True 180 | 181 | # Custom sidebar templates, maps document names to template names. 182 | #html_sidebars = {} 183 | 184 | # Additional templates that should be rendered to pages, maps page names to 185 | # template names. 186 | #html_additional_pages = {} 187 | 188 | # If false, no module index is generated. 189 | #html_domain_indices = True 190 | 191 | # If false, no index is generated. 192 | #html_use_index = True 193 | 194 | # If true, the index is split into individual pages for each letter. 195 | #html_split_index = False 196 | 197 | # If true, links to the reST sources are added to the pages. 198 | #html_show_sourcelink = True 199 | 200 | # If true, "Created using Sphinx" is shown in the HTML footer. Default is True. 201 | #html_show_sphinx = True 202 | 203 | # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. 204 | #html_show_copyright = True 205 | 206 | # If true, an OpenSearch description file will be output, and all pages will 207 | # contain a tag referring to it. The value of this option must be the 208 | # base URL from which the finished HTML is served. 209 | #html_use_opensearch = '' 210 | 211 | # This is the file name suffix for HTML files (e.g. ".xhtml"). 212 | #html_file_suffix = None 213 | 214 | # Output file base name for HTML help builder. 215 | htmlhelp_basename = 'easyML-templatedoc' 216 | 217 | 218 | # -- Options for LaTeX output --------------------------------------------- 219 | 220 | latex_elements = { 221 | # The paper size ('letterpaper' or 'a4paper'). 222 | #'papersize': 'letterpaper', 223 | 224 | # The font size ('10pt', '11pt' or '12pt'). 225 | #'pointsize': '10pt', 226 | 227 | # Additional stuff for the LaTeX preamble. 228 | #'preamble': '', 229 | } 230 | 231 | # Grouping the document tree into LaTeX files. List of tuples 232 | # (source start file, target name, title, 233 | # author, documentclass [howto, manual, or own class]). 234 | latex_documents = [ 235 | ('index', 'easyML-template.tex', u'easyML-template Documentation', 236 | u'Aarshay Jain', 'manual'), 237 | ] 238 | 239 | # The name of an image file (relative to this directory) to place at the top of 240 | # the title page. 241 | #latex_logo = None 242 | 243 | # For "manual" documents, if this is true, then toplevel headings are parts, 244 | # not chapters. 245 | #latex_use_parts = False 246 | 247 | # If true, show page references after internal links. 248 | #latex_show_pagerefs = False 249 | 250 | # If true, show URL addresses after external links. 251 | #latex_show_urls = False 252 | 253 | # Documents to append as an appendix to all manuals. 254 | #latex_appendices = [] 255 | 256 | # If false, no module index is generated. 257 | #latex_domain_indices = True 258 | 259 | 260 | # -- Options for manual page output --------------------------------------- 261 | 262 | # One entry per manual page. List of tuples 263 | # (source start file, name, description, authors, manual section). 264 | man_pages = [ 265 | ('index', 'easyML-template', u'easyML-template Documentation', 266 | [u'Aarshay Jain'], 1) 267 | ] 268 | 269 | # If true, show URL addresses after external links. 270 | #man_show_urls = False 271 | 272 | 273 | # -- Options for Texinfo output ------------------------------------------- 274 | 275 | # Grouping the document tree into Texinfo files. List of tuples 276 | # (source start file, target name, title, author, 277 | # dir menu entry, description, category) 278 | texinfo_documents = [ 279 | ('index', 'easyML-template', u'easyML-template Documentation', 280 | u'Aarshay Jain', 'easyML-template', 'One line description of easyML.', 281 | 'Miscellaneous'), 282 | ] 283 | 284 | def generate_example_rst(app, what, name, obj, options, lines): 285 | # generate empty examples files, so that we don't get 286 | # inclusion errors if there are no examples for a class / module 287 | examples_path = os.path.join(app.srcdir, "modules", "generated", 288 | "%s.examples" % name) 289 | if not os.path.exists(examples_path): 290 | # touch file 291 | open(examples_path, 'w').close() 292 | 293 | 294 | def setup(app): 295 | app.connect('autodoc-process-docstring', generate_example_rst) 296 | 297 | # Documents to append as an appendix to all manuals. 298 | #texinfo_appendices = [] 299 | 300 | # If false, no module index is generated. 301 | #texinfo_domain_indices = True 302 | 303 | # How to display URL addresses: 'footnote', 'no', or 'inline'. 304 | #texinfo_show_urls = 'footnote' 305 | 306 | # If true, do not generate a @detailmenu in the "Top" node's menu. 307 | #texinfo_no_detailmenu = False 308 | 309 | 310 | # Example configuration for intersphinx: refer to the Python standard library. 311 | intersphinx_mapping = {'http://docs.python.org/': None} 312 | 313 | ###CUSTOM SETTINGS: 314 | autodoc_member_order = 'bysource' -------------------------------------------------------------------------------- /doc/datablock.rst: -------------------------------------------------------------------------------- 1 | DataBlock Module 2 | ===================== 3 | 4 | This modules allows you to integrate all you data into a block to allow seemless integration with other modules. Every other module of this package will take a DataBlock instance as input and get all the required information from there. 5 | 6 | 7 | Class Structure 8 | --------------- 9 | 10 | .. autoclass:: easyML.data.DataBlock 11 | :members: data_present,combined_data 12 | .. :member_order: bysource -------------------------------------------------------------------------------- /doc/feature_engineering.rst: -------------------------------------------------------------------------------- 1 | Feature Engineering Module 2 | ========================== 3 | 4 | The feature engineering module is designed to help you create featurs in your data which can potentially boost your model performance. Feture Engineering is a key element in the predictive modeling process. 5 | 6 | Upcoming Features 7 | ----------------- 8 | 9 | - One-Hot-Encoding or creating dummy variables 10 | - Count features 11 | - Interaction features 12 | - Polynomial features 13 | - Transformations 14 | - Row statistics 15 | - Bayesian features 16 | - tSNE feature 17 | 18 | Class Structure 19 | --------------- 20 | 21 | .. autoclass:: easyML.feature_engineering.FeatureEngineering 22 | :members: create_bins, combine_categories 23 | .. :member_order: bysource -------------------------------------------------------------------------------- /doc/index.rst: -------------------------------------------------------------------------------- 1 | .. project-template documentation master file, created by 2 | sphinx-quickstart on Mon Jan 18 14:44:12 2016. 3 | You can adapt this file completely to your liking, but it should at least 4 | contain the root `toctree` directive. 5 | 6 | Welcome to easyML's documentation! 7 | ============================================ 8 | 9 | easyML is a python package designed to streamline the process of analyzing 10 | datasets using predictive models. It covers crutial aspects the of data 11 | analysis process starting from preprocessing, moving to feature engineering 12 | and finally predictive modeling. 13 | 14 | They key advantage of this package is the data block feature using which you can create a block of your data at the start of analysis. Now you can just call different functions which seemlessly integrate with your data. It definitely comes at the cost of loss of generalization as compared to the raw scikit-learn features, but the idea is to have a good coverage and provide options for flexibility. The package is particularly useful for begineers and intermediate level python data science enthusiasts, who are looking to get the job done without worrying about the code. 15 | 16 | Use the following to get started: 17 | 18 | .. toctree:: 19 | :maxdepth: 3 20 | 21 | api 22 | 23 | 24 | How can you contribute? 25 | ======================= 26 | 27 | What you see now is an alpha-version of the package. I have defined a framework with a class structure having clear dataflow. The module contains some fundamental modules. There's still a lot to be done as there are lots of cool modules to be added. I have my upcoming functions list in each module. 28 | 29 | I'm sure if you are a serious analyst/data scientist, you would have many such wrappers of your own. I would love to hear about them and it'll be great if you contrinute your ideas/code. Even if you don't have the code, feel free to add feature requests for things you would like see. 30 | 31 | To get started: 32 | 33 | * Fork the github repo - 34 | * Install package using PyPi - 35 | 36 | 37 | Indices and tables 38 | ================== 39 | 40 | * :ref:`genindex` 41 | * :ref:`modindex` 42 | * :ref:`search` 43 | 44 | -------------------------------------------------------------------------------- /doc/make.bat: -------------------------------------------------------------------------------- 1 | @ECHO OFF 2 | 3 | REM Command file for Sphinx documentation 4 | 5 | if "%SPHINXBUILD%" == "" ( 6 | set SPHINXBUILD=sphinx-build 7 | ) 8 | set BUILDDIR=_build 9 | set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% . 10 | set I18NSPHINXOPTS=%SPHINXOPTS% . 11 | if NOT "%PAPER%" == "" ( 12 | set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS% 13 | set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS% 14 | ) 15 | 16 | if "%1" == "" goto help 17 | 18 | if "%1" == "help" ( 19 | :help 20 | echo.Please use `make ^` where ^ is one of 21 | echo. html to make standalone HTML files 22 | echo. dirhtml to make HTML files named index.html in directories 23 | echo. singlehtml to make a single large HTML file 24 | echo. pickle to make pickle files 25 | echo. json to make JSON files 26 | echo. htmlhelp to make HTML files and a HTML help project 27 | echo. qthelp to make HTML files and a qthelp project 28 | echo. devhelp to make HTML files and a Devhelp project 29 | echo. epub to make an epub 30 | echo. latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter 31 | echo. text to make text files 32 | echo. man to make manual pages 33 | echo. texinfo to make Texinfo files 34 | echo. gettext to make PO message catalogs 35 | echo. changes to make an overview over all changed/added/deprecated items 36 | echo. xml to make Docutils-native XML files 37 | echo. pseudoxml to make pseudoxml-XML files for display purposes 38 | echo. linkcheck to check all external links for integrity 39 | echo. doctest to run all doctests embedded in the documentation if enabled 40 | goto end 41 | ) 42 | 43 | if "%1" == "clean" ( 44 | for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i 45 | del /q /s %BUILDDIR%\* 46 | goto end 47 | ) 48 | 49 | 50 | %SPHINXBUILD% 2> nul 51 | if errorlevel 9009 ( 52 | echo. 53 | echo.The 'sphinx-build' command was not found. Make sure you have Sphinx 54 | echo.installed, then set the SPHINXBUILD environment variable to point 55 | echo.to the full path of the 'sphinx-build' executable. Alternatively you 56 | echo.may add the Sphinx directory to PATH. 57 | echo. 58 | echo.If you don't have Sphinx installed, grab it from 59 | echo.http://sphinx-doc.org/ 60 | exit /b 1 61 | ) 62 | 63 | if "%1" == "html" ( 64 | %SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html 65 | if errorlevel 1 exit /b 1 66 | echo. 67 | echo.Build finished. The HTML pages are in %BUILDDIR%/html. 68 | goto end 69 | ) 70 | 71 | if "%1" == "dirhtml" ( 72 | %SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml 73 | if errorlevel 1 exit /b 1 74 | echo. 75 | echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml. 76 | goto end 77 | ) 78 | 79 | if "%1" == "singlehtml" ( 80 | %SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml 81 | if errorlevel 1 exit /b 1 82 | echo. 83 | echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml. 84 | goto end 85 | ) 86 | 87 | if "%1" == "pickle" ( 88 | %SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle 89 | if errorlevel 1 exit /b 1 90 | echo. 91 | echo.Build finished; now you can process the pickle files. 92 | goto end 93 | ) 94 | 95 | if "%1" == "json" ( 96 | %SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json 97 | if errorlevel 1 exit /b 1 98 | echo. 99 | echo.Build finished; now you can process the JSON files. 100 | goto end 101 | ) 102 | 103 | if "%1" == "htmlhelp" ( 104 | %SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp 105 | if errorlevel 1 exit /b 1 106 | echo. 107 | echo.Build finished; now you can run HTML Help Workshop with the ^ 108 | .hhp project file in %BUILDDIR%/htmlhelp. 109 | goto end 110 | ) 111 | 112 | if "%1" == "qthelp" ( 113 | %SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp 114 | if errorlevel 1 exit /b 1 115 | echo. 116 | echo.Build finished; now you can run "qcollectiongenerator" with the ^ 117 | .qhcp project file in %BUILDDIR%/qthelp, like this: 118 | echo.^> qcollectiongenerator %BUILDDIR%\qthelp\project-template.qhcp 119 | echo.To view the help file: 120 | echo.^> assistant -collectionFile %BUILDDIR%\qthelp\project-template.ghc 121 | goto end 122 | ) 123 | 124 | if "%1" == "devhelp" ( 125 | %SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp 126 | if errorlevel 1 exit /b 1 127 | echo. 128 | echo.Build finished. 129 | goto end 130 | ) 131 | 132 | if "%1" == "epub" ( 133 | %SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub 134 | if errorlevel 1 exit /b 1 135 | echo. 136 | echo.Build finished. The epub file is in %BUILDDIR%/epub. 137 | goto end 138 | ) 139 | 140 | if "%1" == "latex" ( 141 | %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex 142 | if errorlevel 1 exit /b 1 143 | echo. 144 | echo.Build finished; the LaTeX files are in %BUILDDIR%/latex. 145 | goto end 146 | ) 147 | 148 | if "%1" == "latexpdf" ( 149 | %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex 150 | cd %BUILDDIR%/latex 151 | make all-pdf 152 | cd %BUILDDIR%/.. 153 | echo. 154 | echo.Build finished; the PDF files are in %BUILDDIR%/latex. 155 | goto end 156 | ) 157 | 158 | if "%1" == "latexpdfja" ( 159 | %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex 160 | cd %BUILDDIR%/latex 161 | make all-pdf-ja 162 | cd %BUILDDIR%/.. 163 | echo. 164 | echo.Build finished; the PDF files are in %BUILDDIR%/latex. 165 | goto end 166 | ) 167 | 168 | if "%1" == "text" ( 169 | %SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text 170 | if errorlevel 1 exit /b 1 171 | echo. 172 | echo.Build finished. The text files are in %BUILDDIR%/text. 173 | goto end 174 | ) 175 | 176 | if "%1" == "man" ( 177 | %SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man 178 | if errorlevel 1 exit /b 1 179 | echo. 180 | echo.Build finished. The manual pages are in %BUILDDIR%/man. 181 | goto end 182 | ) 183 | 184 | if "%1" == "texinfo" ( 185 | %SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo 186 | if errorlevel 1 exit /b 1 187 | echo. 188 | echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo. 189 | goto end 190 | ) 191 | 192 | if "%1" == "gettext" ( 193 | %SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale 194 | if errorlevel 1 exit /b 1 195 | echo. 196 | echo.Build finished. The message catalogs are in %BUILDDIR%/locale. 197 | goto end 198 | ) 199 | 200 | if "%1" == "changes" ( 201 | %SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes 202 | if errorlevel 1 exit /b 1 203 | echo. 204 | echo.The overview file is in %BUILDDIR%/changes. 205 | goto end 206 | ) 207 | 208 | if "%1" == "linkcheck" ( 209 | %SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck 210 | if errorlevel 1 exit /b 1 211 | echo. 212 | echo.Link check complete; look for any errors in the above output ^ 213 | or in %BUILDDIR%/linkcheck/output.txt. 214 | goto end 215 | ) 216 | 217 | if "%1" == "doctest" ( 218 | %SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest 219 | if errorlevel 1 exit /b 1 220 | echo. 221 | echo.Testing of doctests in the sources finished, look at the ^ 222 | results in %BUILDDIR%/doctest/output.txt. 223 | goto end 224 | ) 225 | 226 | if "%1" == "xml" ( 227 | %SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml 228 | if errorlevel 1 exit /b 1 229 | echo. 230 | echo.Build finished. The XML files are in %BUILDDIR%/xml. 231 | goto end 232 | ) 233 | 234 | if "%1" == "pseudoxml" ( 235 | %SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml 236 | if errorlevel 1 exit /b 1 237 | echo. 238 | echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml. 239 | goto end 240 | ) 241 | 242 | :end 243 | -------------------------------------------------------------------------------- /doc/modules/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/doc/modules/.DS_Store -------------------------------------------------------------------------------- /doc/preprocess.rst: -------------------------------------------------------------------------------- 1 | Pre-Processing Module 2 | ===================== 3 | 4 | The preprocess module is designed to help you perform some basic checks like missing values. It also helps you clearn your data for analysis by providing easy-to-use functions for imputation, scaling data and normalizing the data. It also has a generic apply function to help you 5 | 6 | Upcoming Features 7 | ----------------- 8 | 9 | - Check near-zero variance 10 | - Check duplicates 11 | - Check data types 12 | - Check multi-colinraity 13 | - Split data train-test 14 | - Sense check on data 15 | - Text processing 16 | 17 | Class Structure 18 | --------------- 19 | 20 | .. autoclass:: easyML.preprocess.PreProcess 21 | :members: check_missing, imputation, scale, normalize, apply 22 | .. :member_order: bysource -------------------------------------------------------------------------------- /easyML/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/easyML/.DS_Store -------------------------------------------------------------------------------- /easyML/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/easyML/__init__.py -------------------------------------------------------------------------------- /easyML/base_class.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | from abc import ABCMeta, abstractmethod 6 | 7 | ##################################################################### 8 | ##### DEFINE BASE CLASSES WITH CHECKS AND EXCEPTIONS 9 | ##################################################################### 10 | 11 | class BaseClass(object): 12 | 13 | #Define this as a meta class so that direct objects of this are not possible 14 | __metaclass__ = ABCMeta 15 | 16 | class InvalidInput(Exception): 17 | # Error to be raised when the subset parameter is not a subset of 18 | #the train columns 19 | pass 20 | 21 | def subset_check(self,subset): 22 | if not isinstance(subset,list): 23 | subset = [subset] 24 | if not set(subset).issubset(set(self.datablock.columns)): 25 | raise self.InvalidInput("The subset parameter is not a subset of the dataframes in datablock") 26 | 27 | def check_datatype(self,var,varname,types): 28 | #check whether var belongs to the type 29 | if not (isinstance(var,types)): 30 | raise self.InvalidInput("%s should be %s, found %s"%( 31 | varname, types,type(var)) 32 | ) 33 | 34 | def check_datatype2(self,var,varname,types): 35 | #check whether var belongs to one of 2 types in types 36 | if not (isinstance(var,types[0]) | isinstance(var,types[1])): 37 | raise self.InvalidInput("%s can either be %s or %s, found %s"%( 38 | varname, types[0],types[1],type(var)) 39 | ) 40 | 41 | def check_list_type(self,check_list,types,message): 42 | #check whether each element of list if in given types 43 | for i in check_list: 44 | if not isinstance(i,types): 45 | raise self.InvalidInput(message) 46 | 47 | def check_value_in_range(self,value,range,message): 48 | if value not in range: 49 | raise self.InvalidInput(message) -------------------------------------------------------------------------------- /easyML/data.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | #Python 3 support: 6 | from __future__ import absolute_import, division, print_function, unicode_literals 7 | 8 | import pandas as pd 9 | import numpy as np 10 | import collections #to maintain dp as an ordered dictionary 11 | from .base_class import BaseClass 12 | 13 | ##################################################################### 14 | ##### DEFINE DATA_BLOCK CLASS 15 | ##################################################################### 16 | 17 | class DataBlock(BaseClass): 18 | """ Define the data block which contains the entire set of data. 19 | This is a unique data structure which will be passed as input to 20 | the other classes of this module. This helps in packaging all the 21 | data together so that every action is performed on all the dataframes 22 | together, thus reducing the coding overheads significantly. 23 | 24 | Note: The function will CREATE COPIES of the dataset by default. If the 25 | data size is too big, then you can either pass file-paths from where to 26 | read data or set the makeCopy parameter to False. 27 | 28 | Parameters 29 | __________ 30 | train : pandas dataframe or str 31 | The training data, which is used to train the model. 32 | This data should have both the predictors, i.e. independent data 33 | and the target, i.e. dependent data. 34 | The data can be passed as a pandas dataframe or the filepath to the 35 | .csv file which stores the data. Only .csv extension is supported 36 | for now. 37 | This data has to be provided. 38 | 39 | test : pandas dataframe or str or None 40 | The testing data. 41 | This data should have both the predictors, i.e. independent data 42 | and the target, i.e. dependent data. 43 | This is typically used to evaluate models. This is generally used if 44 | a lot of data is available and it is feasible to split it into train 45 | or test. Otherwise, cross-validation is performed on training data 46 | and there is no explicit test data. 47 | The data can be passed as a pandas dataframe or the filepath to the 48 | .csv file which stores the data. Only .csv extension is supported 49 | for now. 50 | Pass None to the argument if data is not available. 51 | 52 | predict : pandas or str dataframe 53 | The data with unknown labels or targets, which are to be predicted. 54 | This is generally available in online hackathons where it is called 55 | as a test set because true labels are available with the organizers 56 | which are used to evaluate the model. But for the purpose of this 57 | module, any data without known targets should be passed into predict 58 | dataframe because we will make these predictions and export the 59 | results. 60 | The data can be passed as a pandas dataframe or the filepath to the 61 | .csv file which stores the data. Only .csv extension is supported 62 | for now. 63 | Pass None to the argument if data is not available. 64 | 65 | Note that a target column with all None values will be added to this 66 | dataframe by the module to allow integration with other datasets. If 67 | such a column already exists, then its values will be made None. 68 | 69 | target : str 70 | The name of the variable representing the values to be predicted 71 | 72 | ID : str or list of str or None, default None 73 | The name of the variavle(s) which individually/together form a 74 | unique entity for each observation. 75 | This can be left empty at the time of initialization but will inhibit 76 | the functioning of certain methods in the module related to 77 | exporting data. 78 | 79 | makeCopy : bool, default=True 80 | if True, then copies of the dataframes passed into the class 81 | initialization will be created. Otherwise, the function will point 82 | to the same variables as in your environment and they will get 83 | modified by the functions of easyML module. 84 | 85 | Attributes 86 | __________ 87 | train : pandas dataframe 88 | Same as passed values. Provided so that separate copies of data are 89 | not requried. 90 | 91 | test : pandas dataframe 92 | Same as passed values. Provided so that separate copies of data are 93 | not requried. 94 | 95 | predict : pandas dataframe 96 | Same as passed values. Provided so that separate copies of data are 97 | not requried. 98 | 99 | """ 100 | 101 | def __init__( 102 | self, train, test, predict, target, ID=None, makeCopy=True): 103 | 104 | self.check_datatype2(train,'train',(str,pd.DataFrame)) 105 | if makeCopy: 106 | self.train = pd.DataFrame(train,copy=True) 107 | else: 108 | self.train = train 109 | 110 | if test is not None: 111 | self.check_datatype2(test,'test',(str,pd.DataFrame)) 112 | if makeCopy: 113 | self.test = pd.DataFrame(test,copy=True) 114 | else: 115 | self.test = test 116 | 117 | if predict is not None: 118 | self.check_datatype2(predict,'predict',(str,pd.DataFrame)) 119 | if makeCopy: 120 | self.predict = pd.DataFrame(predict,copy=True) 121 | else: 122 | self.predict = predict 123 | 124 | self.target = target 125 | self.ID = ID 126 | 127 | #check data and initialize columns: 128 | self.check_data() 129 | 130 | #get columns: 131 | self.update_column_list() 132 | 133 | def update_column_list(self): 134 | self.columns = list(self.train.columns) 135 | self.numeric_columns = list(self.train._get_numeric_data().columns) 136 | self.other_columns = list(set(self.columns).difference(set(self.numeric_columns))) 137 | 138 | class InvalidDataBlock(Exception): 139 | #""" Raise Exception when the data passed to the datablock is not valid """ 140 | pass 141 | 142 | def check_data(self): 143 | #Check if train and test have same columns: 144 | if self.test is not None: 145 | if set(self.train.columns) != set(self.test.columns): 146 | raise self.InvalidDataBlock("The train and test dataframe should have the equal number of columns with the same names") 147 | 148 | #Check if predict has a subset of columns from train and everything 149 | #except target: 150 | if self.predict is not None: 151 | #Make target column in predict to None or add it not there 152 | self.predict[self.target] = None 153 | if set(self.train.columns) != set(self.predict.columns): 154 | raise self.InvalidDataBlock("The predict dataframe should contain same columns as train with/without the target column") 155 | 156 | 157 | def data_present(self): 158 | """ Get a dictionary with key as the name of the data (train/test/ 159 | predict) and value has the actual data. 160 | Only the dataframe available are returned 161 | 162 | Returns 163 | __________ 164 | dictionary : dict 165 | A dictionary with key as the name of the data (train/test/ 166 | predict) and value has the actual data 167 | """ 168 | dfs = collections.OrderedDict({'train':self.train}) 169 | if self.test is not None: 170 | dfs['test']=self.test 171 | if self.predict is not None: 172 | dfs['predict']=self.predict 173 | return dfs 174 | 175 | def combined_data(self, addSource=False): 176 | """ Get a dataframe with all dataframes combined into one. 177 | Only the dataframe available are returned. 178 | 179 | Parameters 180 | __________ 181 | addSource : bool, default=False 182 | if True, a column names 'source' will be added containing the 183 | name of the data (train/test/predict) to which the particular 184 | observation belongs. 185 | Note: if a column named source already exists, it will be 186 | overwritten. 187 | 188 | Returns 189 | __________ 190 | df : pandas dataframe 191 | A combined dataframe containg observation from all dataframes 192 | in the datablock. 193 | Note that the values of the target variable for predict dataframe 194 | will be None 195 | """ 196 | new_df = pd.concat(self.data_present(),axis=0,ignore_index=True) 197 | 198 | if addSource: 199 | source = [] 200 | for key,data in self.data_present(): 201 | source.append([key]*data.shape[0]) 202 | new_df['source'] = source 203 | 204 | return new_df 205 | 206 | -------------------------------------------------------------------------------- /easyML/feature_engineering.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | #Python 3 support: 6 | from __future__ import absolute_import, division 7 | from __future__ import print_function, unicode_literals 8 | 9 | import pandas as pd 10 | import numpy as np 11 | import matplotlib.pyplot as plt 12 | from scipy.stats import mode 13 | import warnings 14 | 15 | from .base_class import BaseClass 16 | from .data import DataBlock 17 | 18 | ##################################################################### 19 | ##### DEFINE PREPROCESS CLASS 20 | ##################################################################### 21 | 22 | class FeatureEngineering(BaseClass): 23 | """ A feature engineering module which helps you create new features 24 | into the data using the easy-to-use built-in modules. The features 25 | are created on all 3 of the dataframes in datablock simultaneously. 26 | 27 | Parameters 28 | ---------- 29 | data_block : object of type DataBlock 30 | An object of easyML's DataBlock class. You should first create an 31 | object of that class and then pass it as a parameter. 32 | 33 | Attributes 34 | ---------- 35 | datablock : object of type DataBlock 36 | The pre-processed data containing all the modifications made 37 | using the module's methods 38 | """ 39 | def __init__(self, data_block): 40 | 41 | #check if data element is of class datablock 42 | self.check_datatype(data_block,'data_block',DataBlock) 43 | 44 | self.datablock = data_block 45 | self.target = self.datablock.target #though redundant but will make code mode readable 46 | 47 | #get tuple of available data 48 | self.dp = self.datablock.data_present().values() 49 | 50 | 51 | def create_bins( 52 | self,column, cut_points,labels=None, inplace=True, suffix='_bin'): 53 | """ Used to create a categorical feature from a numeric feature by 54 | binning specific ranges of numbers together. 55 | 56 | Parameters 57 | __________ 58 | column : str 59 | This represents the column on which the function is to be applied 60 | 61 | cut_points : list of num 62 | This represents a list of numbers at which the data has to be 63 | cut. For example, an input [5,10] will divide the column into 3 64 | categories: [(-inf,5],(5,10],(10,inf)] 65 | 66 | labels : list of str or None, default=None 67 | User-defined labels for the resulting category in increasing 68 | order. The length of the list should be 1 more than the length 69 | of cuts_points. 70 | If None, then default labels are 0, 1, ..., n-1. Note that an 71 | object type feature is formed if custom labels provided, 72 | otherwise the returned columns is of type numeric by default. 73 | 74 | inplace : bool, default=True 75 | If True, then the original column in the data will be modified. 76 | If False, then a new column will be created with a suffix as 77 | specified by suffix parameter. 78 | 79 | suffix : str, default='_bin' 80 | If inplace argument is False, then this is the suffix applied to 81 | the column name to creat a new column. 82 | Note that if such a column already exists, it will be overwritten 83 | """ 84 | 85 | #check: 86 | self.check_datatype(column,'column',basestring) 87 | self.check_datatype(cut_points,'cut_points',list) 88 | self.check_datatype(inplace,'inplace',bool) 89 | self.check_datatype(suffix,'suffix',basestring) 90 | 91 | if labels: 92 | self.check_datatype(labels,'labels',list) 93 | if len(labels) != len(cut_points)+1: 94 | raise self.InvalidInput("Length of labels (%d) should be 1 more than the length of cut_points (%d)"%(len(labels),len(cut_points))) 95 | 96 | self.subset_check(column) 97 | 98 | #Define tag for converting to numeric: 99 | change_to_num = False 100 | 101 | #Define min and max values: 102 | min_val = min([data[column].min() for data in self.dp]) 103 | max_val = max([data[column].max() for data in self.dp]) 104 | 105 | #create list by adding min and max to cut_points 106 | break_points = [min_val] + cut_points + [max_val] 107 | 108 | #if no labels provided, use default labels 0 ... (n-1) 109 | if not labels: 110 | labels = range(len(cut_points)+1) 111 | change_to_num=True 112 | 113 | if inplace: 114 | new_var = column 115 | else: 116 | new_var = "".join([column,suffix]) 117 | 118 | #Bin all datasets: 119 | for data in self.dp: 120 | data[new_var] = pd.cut( 121 | data[column], bins=break_points, 122 | labels=labels, include_lowest=True 123 | ) 124 | if change_to_num: 125 | data[new_var] = data[new_var].apply(lambda x: int(x)) 126 | 127 | def combine_categories( 128 | self,column, combine_dict, inplace=True, suffix='_combined'): 129 | """ Used to comine categories of a categorical feature. 130 | Note that only the categories specified in the combine_dict will be 131 | changed and rest all will remain as it is. 132 | 133 | Parameters 134 | __________ 135 | column : str 136 | This represents the column on which the function is to be applied 137 | 138 | combine_dict : dict 139 | This represents the replacement dictionary of the form 140 | {'new_categories':[list of old categories]} where the dictionary 141 | keys represents the new categories to be created and the values 142 | represent the old categories which are to be combined to get the 143 | new one. 144 | For example, {'d':['a','b','c']} will combine all 'a','b','c' to 145 | give just 1 category 'd', which might be a pre-existing category 146 | or a new one. 147 | 148 | inplace : bool, default=True 149 | If True, then the original column in the data will be modified. 150 | If False, then a new column will be created with a suffix as 151 | specified by suffix parameter. 152 | 153 | suffix : str, default='_combined' 154 | If inplace argument is False, then this is the suffix applied to 155 | the column name to creat a new column. 156 | Note that if such a column already exists, it will be overwritten 157 | """ 158 | 159 | #check: 160 | self.check_datatype(column,'column',basestring) 161 | self.check_datatype(combine_dict,'combine_dict',dict) 162 | self.check_datatype(inplace,'inplace',bool) 163 | self.check_datatype(suffix,'suffix',basestring) 164 | 165 | self.subset_check(column) 166 | 167 | #Check each value is a list: 168 | self.check_list_type( 169 | combine_dict.values(),list, 170 | "Each value of the combine_dict should be a list") 171 | 172 | replace_dict={} 173 | #dictionary comprehension to form a reverse dictionary with keys as 174 | #the old value and value as new value. 175 | [replace_dict.update({val:key}) 176 | for key,values in combine_dict.items() 177 | for val in values] 178 | 179 | if inplace: 180 | new_var = column 181 | else: 182 | new_var = "".join([column,suffix]) 183 | for data in self.dp: 184 | data[new_var] = data[column] 185 | 186 | for data in self.dp: 187 | data[new_var].replace(replace_dict,inplace=True) 188 | 189 | -------------------------------------------------------------------------------- /easyML/genericmodelclass.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | import pandas as pd 6 | import numpy as np 7 | import matplotlib.pyplot as plt 8 | from sklearn.model_selection import KFold, GridSearchCV 9 | from sklearn import metrics, model_selection 10 | from sklearn.feature_selection import RFE, RFECV 11 | from abc import ABCMeta, abstractmethod 12 | 13 | from .base_class import BaseClass 14 | 15 | ##################################################################### 16 | ##### GENERIC MODEL CLASS 17 | ##################################################################### 18 | 19 | class GenericModelClass(BaseClass): 20 | """ This class contains the generic classification functionms and variable definitions applicable across all models 21 | """ 22 | 23 | #Define as a meta class to disable direct instances 24 | __metaclass__ = ABCMeta 25 | 26 | #Empty dictionary for default parameters to be updated in inhereted 27 | #class: 28 | default_parameters = {} 29 | 30 | def __init__( 31 | self, alg, data_block, predictors=[],cv_folds=5, 32 | scoring_metric='accuracy',additional_display_metrics=[]): 33 | 34 | self.alg = alg 35 | self.datablock = data_block 36 | self.cv_folds = cv_folds 37 | self.predictors = predictors 38 | self.predictions_class = {} 39 | 40 | #define scoring metric: 41 | self.scoring_metric = scoring_metric 42 | self.additional_display_metrics=additional_display_metrics 43 | 44 | #grid-search objects: 45 | self.gridsearch_class = None 46 | self.gridsearch_result = None 47 | 48 | #not to be used for all but most 49 | self.feature_imp = None 50 | 51 | #Modify and get predictors for the model: 52 | def set_predictors(self, predictors): 53 | """ Set the columns to be used predictors (also called independent 54 | variables or features) of the model. 55 | 56 | Parameters 57 | ---------- 58 | predictors : list of strings 59 | A list of columns which are to be used as predictors (also 60 | called independent variables or features). 61 | """ 62 | self.predictors=predictors 63 | 64 | 65 | def set_scoring_metric(scoring_metric, additional_display_metrics=[]): 66 | """ A method to update the metric to be used for scoring the 67 | models and some additional metric just for reference if required. 68 | 69 | Parameters 70 | ---------- 71 | scoring_metric : str 72 | This is same as in model class. 73 | 74 | additional_display_metrics : list of str 75 | This is same as in model class. 76 | If nothing specified, then the original values will not be 77 | modified 78 | """ 79 | self.scoring_metric = scoring_metric 80 | if additional_display_metrics: 81 | self.additional_display_metrics = additional_display_metrics 82 | 83 | 84 | def KFold_CrossValidation(self, scoring_metric): 85 | # Generate cross validation folds for the training dataset. 86 | 87 | error = model_selection.cross_val_score( 88 | estimator=self.alg, 89 | X=self.datablock.train[self.predictors].values, 90 | y=self.datablock.train[self.datablock.target].values, 91 | cv=self.cv_folds, scoring=scoring_metric, n_jobs=-1 92 | ) 93 | 94 | return { 95 | 'mean_error': np.mean(error), 96 | 'std_error': np.std(error), 97 | 'all_error': error 98 | } 99 | 100 | 101 | def recursive_feature_elimination(self, nfeat=None, step=1, inplace=False): 102 | 103 | """A method to implement recursive feature elimination on the model. 104 | Note that CV is not performed in this function. The method will 105 | continue to eliminate some features (specified by step parameter) 106 | at each step until the specified number of features are reached. 107 | 108 | Parameters 109 | __________ 110 | nfeat : int or None, default=None 111 | The num of top features to select. If None, half of the features 112 | are selected. 113 | 114 | step : int or float, default=1 115 | If int, then step corresponds to the number of features to remove 116 | at each iteration. 117 | If float and within (0.0, 1.0), then step corresponds to the 118 | percentage (rounded down) of features to remove at each 119 | iteration. 120 | If float and greater than one, then integral part will be 121 | considered as an integer input 122 | 123 | inplace : bool, default=False 124 | If True, the predictors of the class are modified to those 125 | selected by the RFE procedure. 126 | 127 | Returns 128 | _______ 129 | selected : A series object containing the selected features as 130 | index and their rank in selection as values 131 | """ 132 | rfe = RFE(self.alg, n_features_to_select=nfeat, step=step) 133 | 134 | rfe.fit( 135 | self.datablock.train[self.predictors], 136 | self.datablock.train[self.datablock.target] 137 | ) 138 | 139 | ranks = pd.Series(rfe.ranking_, index=self.predictors) 140 | 141 | selected = ranks.loc[rfe.support_] 142 | 143 | if inplace: 144 | self.set_predictors(selected.index.tolist()) 145 | 146 | return selected 147 | 148 | 149 | def recursive_feature_elimination_cv(self, step=1, inplace=False): 150 | """A method to implement recursive feature elimination on the model 151 | with cross-validation(CV). At each step, features are ranked as per 152 | the algorithm used and lowest ranked features are removed, 153 | as specified by the step argument. At each step, the CV score is 154 | determined using the scoring metric specified in the model. The set 155 | of features with highest cross validation scores is then chosen. 156 | 157 | Parameters 158 | __________ 159 | step : int or float, default=1 160 | If int, then step corresponds to the number of features to remove 161 | at each iteration. 162 | If float and within (0.0, 1.0), then step corresponds to the 163 | percentage (rounded down) of features to remove at each 164 | iteration. 165 | If float and greater than one, then integral part will be 166 | considered as an integer input 167 | 168 | inplace : bool, default=False 169 | If True, the predictors of the class are modified to those 170 | selected by the RFECV procedure. 171 | 172 | Returns 173 | _______ 174 | selected : pandas series 175 | A series object containing the selected features as 176 | index and their rank in selection as values 177 | """ 178 | rfecv = RFECV( 179 | self.alg, step=step,cv=self.cv_folds, 180 | scoring=self.scoring_metric,n_jobs=-1 181 | ) 182 | 183 | rfecv.fit( 184 | self.datablock.train[self.predictors], 185 | self.datablock.train[self.datablock.target] 186 | ) 187 | 188 | if step>1: 189 | min_nfeat = (len(self.predictors) 190 | - step*(len(rfecv.grid_scores_)-1)) 191 | 192 | plt.xlabel("Number of features selected") 193 | plt.ylabel("Cross validation score") 194 | plt.plot( 195 | range(min_nfeat, len(self.predictors)+1, step), 196 | rfecv.grid_scores_ 197 | ) 198 | plt.show(block=False) 199 | 200 | ranks = pd.Series(rfecv.ranking_, index=self.predictors) 201 | selected = ranks.loc[rfecv.support_] 202 | 203 | if inplace: 204 | self.set_predictors(selected.index.tolist()) 205 | return ranks 206 | 207 | 208 | def grid_search( 209 | self, param_grid, n_jobs=1,iid=True, cv=5, getResults=False): 210 | """A method to perform GridSearch with cross-validation (CV) to find 211 | the optimum parameters for the model. 212 | 213 | Parameters 214 | __________ 215 | param_grid : dict 216 | A dictionary with parameters names (string) as keys and lists of 217 | parameter settings to try as values. 218 | Example: for a decision tree, {'max_depth':[3,4,5], 219 | 'min_samples_split':[30,50,100]} will check all the 9 possible 220 | combinations of parameters 221 | 222 | n_jobs : int, default=1 223 | The number of jobs to run in parallel 224 | 225 | iid : bool, default=True 226 | If True, the data is assumed to be identically distributed across 227 | the folds, and the loss minimized is the total loss per sample, 228 | and not the mean loss across the folds. 229 | 230 | cv : int, default=5 231 | The number of cross-validation folds to generate for testing each 232 | set of parameters 233 | 234 | getResults : bool, default=False 235 | If True, a pandas dataframe containing the results of the grid 236 | search will be returned 237 | 238 | Returns 239 | _______ 240 | gridsearch_results : pandas dataframe 241 | The pandas dataframe containing the grid-search results. 242 | """ 243 | self.gridsearch_class = GridSearchCV( 244 | self.alg, param_grid=param_grid, scoring=self.scoring_metric, 245 | n_jobs=n_jobs, iid=iid, cv=cv) 246 | 247 | self.gridsearch_class.fit( 248 | self.datablock.train[self.predictors], 249 | self.datablock.train[self.datablock.target] 250 | ) 251 | 252 | self.gridsearch_result = pd.DataFrame( 253 | self.gridsearch_class.cv_results_) 254 | 255 | print('Grid Search Results:') 256 | print(self.gridsearch_result[ 257 | ['params','mean_test_score','std_test_score', 258 | 'mean_train_score','std_train_score'] 259 | ]) 260 | print('\nBest Parameters: ', self.gridsearch_class.best_params_) 261 | print('\nBest Score: ', self.gridsearch_class.best_score_) 262 | 263 | if getResults: 264 | return self.gridsearch_result 265 | 266 | 267 | def submission(self, IDcol, filename="submission.csv"): 268 | """This method creates a submission file (mostly used for online 269 | hackathons) with the prediction classes. 270 | 271 | Parameters 272 | __________ 273 | IDcol : str or list of str 274 | The column names to be present in the exported file apart from 275 | the prediction columns. They generally represent the unique IDs 276 | of each observation or row. 277 | 278 | filename : str, default="submission.csv" 279 | The name of the file, along with the path, which will contain 280 | the submission results. The exported file will have the columns 281 | mentioned in the IDcol parameter along with column representing 282 | the predicted class. 283 | """ 284 | 285 | if not isinstance(IDcol,list): 286 | IDcol = [IDcol] 287 | submission = pd.DataFrame( 288 | { x: self.datablock.test[x] for x in IDcol } 289 | ) 290 | #The output is typecasted to integer specifically so that the csv 291 | # file doesn't read the format wrong 292 | submission[self.datablock.target] = \ 293 | self.predictions['predict'].astype(int) 294 | submission.to_csv(filename, index=False) 295 | 296 | 297 | def create_ensemble_dir(self): 298 | #checks whether the ensemble directory exists and creates one if 299 | #it doesn't 300 | ensdir = os.path.join(os.getcwd(), 'ensemble') 301 | if not os.path.isdir(ensdir): 302 | os.mkdir(ensdir) 303 | 304 | # Define abstract classes which the classes which inheret this will implement: 305 | @abstractmethod 306 | def set_parameters(self): 307 | pass 308 | 309 | @abstractmethod 310 | def fit_model(self): 311 | pass 312 | 313 | @abstractmethod 314 | def export_model(self): 315 | pass -------------------------------------------------------------------------------- /easyML/preprocess.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | #Python 3 support: 6 | from __future__ import absolute_import, division 7 | from __future__ import print_function, unicode_literals 8 | 9 | import pandas as pd 10 | import numpy as np 11 | from scipy.stats import mode 12 | import warnings 13 | import collections 14 | 15 | from .base_class import BaseClass 16 | from .data import DataBlock 17 | 18 | ##################################################################### 19 | ##### DEFINE PREPROCESS CLASS 20 | ##################################################################### 21 | 22 | class PreProcess(BaseClass): 23 | """ A preprocessing modules which helps you preprocess you data 24 | using the easy-to-use built-in modules. The preprocessing is 25 | done on all 3 of the dataframes in datablock simultaneously. 26 | 27 | Parameters 28 | ---------- 29 | data_block : object of type DataBlock 30 | An object of easyML's DataBlock class. You should first create an 31 | object of that class and then pass it as a parameter. 32 | 33 | Attributes 34 | ---------- 35 | datablock : object of type DataBlock 36 | The pre-processed data containing all the modifications made 37 | using the module's methods 38 | """ 39 | def __init__(self, data_block): 40 | 41 | #check if data element is of class datablock 42 | self.check_datatype(data_block,'data_block',DataBlock) 43 | 44 | self.datablock = data_block 45 | #though redundant but will make code mode readable 46 | self.target = self.datablock.target 47 | 48 | #get tuple of available data 49 | self.dp = self.datablock.data_present().values() 50 | 51 | def check_missing( 52 | self, subset=None, printResult=True, returnResult=False): 53 | """ Checks the missing values in the all dataframes. 54 | The target column in the predict variable will not be 55 | checked here because it is assumed to have all missing values. 56 | 57 | Parameters 58 | __________ 59 | subset : list of str or None, default=None 60 | A list specifying the subset of columns in which the missing 61 | values are to be checked. 62 | If None, all columns checked 63 | 64 | printResult : bool, default=True 65 | if True, the result will be printed 66 | 67 | returnResult : bool, default=False 68 | if True, the function will return a dictionary with keys as the 69 | name of the dataset (train/test/predict) and values as a series 70 | object with index as column name and values as the number of 71 | missing values in that column. It will contain all columns even 72 | if they have 0 missing values. 73 | 74 | Returns 75 | _______ 76 | missing_values : tuple with 3 elements 77 | Returns a tuple of 3 pandas series objects pertaining to the 78 | train, test and predict dataframes. Each series has index as the 79 | name of the columns having missing values and values as the 80 | number of missing values in the column. 81 | Returns (None,None,None) if no missing values found. 82 | Nothing is returned is returnSeries argument is False 83 | """ 84 | 85 | #Check if subset is actually a subset of the parameters or not: 86 | if subset: 87 | self.subset_check(subset) 88 | else: 89 | subset = self.datablock.columns 90 | 91 | check_dict = {} 92 | for key,data in self.datablock.data_present().items(): 93 | miss_val = data[subset].apply(lambda x: sum(x.isnull())) 94 | if key=='predict': 95 | #Remove target index if present: 96 | if self.target in miss_val: 97 | miss_val.drop(self.target,inplace=True) 98 | check_dict[key] = miss_val 99 | 100 | if printResult: 101 | for df,miss in check_dict.items(): 102 | if sum(miss)==0: 103 | print('\nNo missing value found in %s dataframe'%df) 104 | else: 105 | print('''\nTotal %d missing values found in %s dataframe 106 | in following columns:'''%(sum(miss),df)) 107 | print(pd.DataFrame( 108 | miss[miss>0], 109 | columns=['Num Missing Values']) 110 | ) 111 | 112 | if returnResult: 113 | return check_dict 114 | 115 | 116 | def imputation( 117 | self, column, metric=None, groupby=None, constant=None, 118 | inplace=True, suffix='_imputed'): 119 | """ Used to performs imputation on a column. The imputation is 120 | performed on all dataframes together. For instance, if a median 121 | imputation is performed, then median of the train dataframe is 122 | determined and the same value used to impute the test and predict 123 | dataframes as well. 124 | 125 | Parameters 126 | __________ 127 | column : str 128 | The name of the column to be imputed. 129 | 130 | metric : str or None, default=None 131 | The metric to be used for imputation. Possible options: 132 | - mean: impute with column mean (only for numeric columns) 133 | - median: impute with column median; default for numeric data 134 | (only for numeric columns) 135 | - mode: impute with column model default for non-numeric data 136 | (only for non-numeric columns) 137 | 138 | groupby : str or list of str or None, default=None 139 | The list of columns by which the metric is to be grouped for 140 | imputation. Note that these columns should not have any misssing 141 | values. 142 | 143 | constant : no constraint, default=None 144 | To be used if a constant user-defined value is to be used for 145 | imputation. This is ignored if metric is not None. 146 | 147 | inplace : bool, default=True 148 | If True, then the original column in the data will be imputed. 149 | If False, then a new column will be created with a suffix as 150 | specified by suffix parameter. This can be used to test 151 | different imputation metrics. 152 | 153 | suffix : str, default='_imputed' 154 | If inplace argument is False, then this is the suffix applied to 155 | the column name to creat a new column. 156 | Note that if such a column already exists, it will be overwritten 157 | """ 158 | 159 | #Perform checks: 160 | self.check_datatype(column,'column',basestring) 161 | if metric: 162 | self.check_value_in_range( 163 | metric, 164 | ['mean','mediam','mode'], 165 | 'The metric can only be "mean","median" or "mode", found %s'%metric 166 | ) 167 | self.check_datatype(inplace,'inplace',bool) 168 | self.check_datatype(suffix,'suffix',basestring) 169 | 170 | self.subset_check(column) 171 | 172 | if groupby: 173 | for col in groupby: 174 | self.subset_check(col) 175 | if sum([sum(x[col].isnull()) for x in self.dp]): 176 | raise ValueError('The groupby column %s contains missing values. Please impute that first.'%col) 177 | 178 | if inplace: 179 | new_var = column 180 | else: 181 | new_var = "".join([column,suffix]) 182 | for data in self.dp: 183 | data[new_var] = data[column] 184 | self.datablock.update_column_list() 185 | 186 | # If constant value passed, then exit the function with that 187 | # imputation 188 | if constant: 189 | warnings.warn('Missing values being imputed with the constant value passed in metrics argument') 190 | for data in self.dp: 191 | data[new_var].fillna(metric,inplace=True) 192 | return 193 | 194 | #Define a function to impute by groups if such selected 195 | def fill_grps(impute_grps): 196 | for data in self.dp: 197 | for i, row in data.loc[ 198 | data[column].isnull(), 199 | [column]+groupby 200 | ].iterrows(): 201 | x = tuple(row.loc[groupby]) 202 | data.loc[i,new_var] = impute_grps.loc[x] 203 | 204 | #Case1: continuous column 205 | if column in self.datablock.numeric_columns: 206 | if metric is not None: 207 | if metric not in ['mean','median']: 208 | raise ValueError('metric can only be mean or median for numeric column') 209 | else: 210 | metric = 'median' 211 | 212 | #check constant input: 213 | #Impute by mean: 214 | if metric == "mean": 215 | if groupby is not None: 216 | #impute groups to be determined on basis of train data 217 | #only not any other data 218 | impute_grps = self.datablock.train.pivot_table( 219 | values=column, index=groupby, aggfunc=np.mean, 220 | fill_value=self.datablock.train[column].median() 221 | ) 222 | fill_grps(impute_grps) 223 | else: 224 | impute_val =self.datablock.train[column].mean() 225 | for data in self.dp: 226 | data[new_var].fillna(impute_val,inplace=True) 227 | 228 | #Impute by median: 229 | elif metric == "median": 230 | if groupby is not None: 231 | #impute groups to be determined on basis of train data 232 | #only not any other data 233 | impute_grps = self.datablock.train.pivot_table( 234 | values=column, index=groupby, aggfunc=np.median, 235 | fill_value=self.datablock.train[column].median() 236 | ) 237 | fill_grps(impute_grps) 238 | else: 239 | impute_val =self.datablock.train[column].median() 240 | for data in self.dp: 241 | data[new_var].fillna(impute_val,inplace=True) 242 | 243 | #Case2: Categorical variable: 244 | if column in self.datablock.other_columns: 245 | 246 | if metric is not None: 247 | if metric not in ['mode']: 248 | raise ValueError('metric can only be mode for non-numeric column') 249 | else: 250 | metric = 'mode' 251 | 252 | #Define the custom functino to determine the mode using scipy's 253 | #mode function 254 | def cust_mode(x): 255 | return mode(x).mode[0] 256 | 257 | #Impute by mode: 258 | if metric == "mode": 259 | if groupby is not None: 260 | #impute groups to be determined on basis of train data 261 | #only not any other data 262 | impute_grps = self.datablock.train.pivot_table( 263 | values=column, index=groupby, aggfunc=cust_mode, 264 | fill_value=cust_mode(self.datablock.train[column]) 265 | ) 266 | fill_grps(impute_grps) 267 | else: 268 | impute_val = cust_mode(self.datablock.train[column]) 269 | for data in self.dp: 270 | data[new_var].fillna(impute_val,inplace=True) 271 | 272 | def scale(self,subset,scale_range=(0,1),inplace=True,suffix='_scaled'): 273 | """ Used to scale the data within a fixed range of values. 274 | 275 | Parameters 276 | __________ 277 | subset : str or list of str 278 | This represents the columns to be scaled. 2 options: 279 | - str: a single column to be scaled 280 | - list of str: list of multiple columns to be scaled 281 | 282 | scale_range : tuple or dictionary, default=(0,1) 283 | This represents the range to which the data is to be scaled. 284 | 2 options: 285 | - tuple (min,mex): fixed range for all columns mentioned in subset 286 | - dictionary : a dictionary with keys as columns mentioned in 287 | subset list and values as the range to which that column is to 288 | be scaled. Note that this works only if subset is entered as a 289 | list of strings 290 | 291 | inplace : bool, default=True 292 | If True, the dataframes will be modified and columns scaled. 293 | If False, new columns will be created with suffix as specified 294 | in suffix parameter 295 | 296 | suffix : str, default='_scaled' 297 | If inplace argument is False, then this is the suffix applied to 298 | the column name to creat a new column. 299 | Note that if such a column already exists, it will be overwritten 300 | """ 301 | 302 | #check: 303 | 304 | self.check_datatype2(subset,'subset',(basestring,list)) 305 | self.check_datatype2(scale_range,'scale_range',(tuple,dict)) 306 | self.check_datatype(inplace,'inplace',bool) 307 | self.check_datatype(suffix,'suffix',basestring) #basestring works for both python2 and python3 308 | 309 | self.subset_check(subset) 310 | 311 | if isinstance(subset,str): 312 | subset = [subset] 313 | 314 | #Iterate over all columns and scale them: 315 | for column in subset: 316 | if isinstance(scale_range,tuple): 317 | r = scale_range 318 | else: 319 | if column not in scale_range: 320 | raise KeyError("%s not found in the dictionary range"%column) 321 | r = scale_range[column] 322 | 323 | #check each tuple of size 2: 324 | if len(r)!=2: 325 | raise InvalidInput("range should contain tuples of fixed size 2. tuple of size %d found"%len(r)) 326 | 327 | #check second element always greater than the first 328 | if r[0]>=r[1]: 329 | raise InvalidInput("each range tuple should be of form (min,max) where min0: 390 | raise self.InvalidInput("The %s column contains missing values, please impute first!"%column) 391 | 392 | if inplace: 393 | new_var = column 394 | else: 395 | new_var = "".join([column,suffix]) 396 | for data in self.dp: 397 | data[new_var] = data[column] 398 | 399 | #Get min and max values: 400 | if norm=='l1': 401 | divisor = sum([sum([abs(x) for x in data[column]]) for data in self.dp]) 402 | else: 403 | divisor = np.sqrt(sum([sum([x**2 for x in data[column]]) for data in self.dp])) 404 | 405 | for data in self.dp: 406 | data[new_var] = data[new_var] / divisor 407 | 408 | #Update the list of columns if inplace False 409 | if not inplace: 410 | self.datablock.update_column_list() 411 | 412 | def apply( 413 | self, column, func, rowwise=True, inplace=True, 414 | suffix='_modified', combine_data=False): 415 | """ Used to apply any function on the data to allow flexibility in 416 | preprocessing part by incorporating functions not directly included 417 | in this package. Note that your function should be able to handle 418 | missing values in data if they exist. 419 | 420 | Parameters 421 | __________ 422 | column : str 423 | This represents the column on which the function is to be applied 424 | 425 | func : pre-defined function 426 | A function which can be of 2 types: 427 | 1. Takes a single value as input and returns a single value. 428 | This function will be applied to each observation independently 429 | and applicable if rowwise=True 430 | 2. Takes a list of numbers as input and returns a list of same 431 | size. This will be applied to entire column at same time and 432 | applicable if rowwise=False 433 | 434 | rowwise : bool, default=True 435 | if True, a function of type1 should be passed else function of 436 | type2 437 | 438 | inplace : bool, default=True 439 | If True, the dataframes will be modified. 440 | If False, new columns will be created with suffix as specified 441 | in suffix parameter 442 | 443 | suffix : str, default='_modified' 444 | If inplace argument is False, then this is the suffix applied to 445 | the column name to creat a new column. 446 | Note that if such a column already exists, it will be overwritten 447 | 448 | combine_data : bool, default=False 449 | Works only in case of rowwise=False. If yes, the type 2 function 450 | will be applied on the combined dataset together, ie. a vector 451 | with observations of all the 3 datasets concatenated will be 452 | passed to it and it should return a vector with numbers in the 453 | same order so that they can be mapped back. 454 | """ 455 | 456 | #check: 457 | self.check_datatype(column,'column',basestring) 458 | if not callable(func): 459 | raise self.InvalidInput("The func parameter should be a callable function") 460 | self.check_datatype(rowwise,'rowwise',bool) 461 | self.check_datatype(inplace,'inplace',bool) 462 | self.check_datatype(suffix,'suffix',basestring) 463 | 464 | self.subset_check(column) 465 | 466 | if inplace: 467 | new_var = column 468 | else: 469 | new_var = "".join([column,suffix]) 470 | for data in self.dp: 471 | data[new_var] = data[column] 472 | 473 | 474 | #function to apply func as per rowwise: 475 | def applyfunc(df,col,rowwise): 476 | if rowwise: 477 | return df[col].apply(func) 478 | else: 479 | return func(list(df[col].values)) 480 | 481 | if combine_data: 482 | #get tuple of available data 483 | result = applyfunc(self.datablock.combined_data(),column,rowwise) 484 | print(result) 485 | ind=0 486 | for data in self.dp: 487 | data[new_var] = result[ind:ind+data.shape[0]] 488 | ind=data.shape[0] 489 | else: 490 | for data in self.dp: 491 | data[new_var] = applyfunc(data,column,rowwise) 492 | 493 | #Update the list of columns if inplace False 494 | if not inplace: 495 | self.datablock.update_column_list() 496 | 497 | -------------------------------------------------------------------------------- /easyML/tests/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/easyML/tests/.DS_Store -------------------------------------------------------------------------------- /easyML/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thismlguy/easyML/d65d4776704c4e417374ff8fb0266b066da51757/easyML/tests/__init__.py -------------------------------------------------------------------------------- /easyML/tests/conftest.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | from ..data import DataBlock 6 | 7 | import pandas as pd 8 | from sklearn.datasets import load_iris 9 | import pytest 10 | 11 | ##################################################################### 12 | ##### DEFINE FIXTURES 13 | ##################################################################### 14 | 15 | @pytest.fixture(scope='module') 16 | def datablock(): 17 | X,y = load_iris(return_X_y=True) 18 | df = pd.DataFrame(X,columns=['var%d'%i for i in range(4)]) 19 | df['target'] = y 20 | 21 | #make 1 variable categorical 22 | df['var3'] = df['var3'].apply(lambda x: int(x)).astype(object) 23 | 24 | #make outcome binary 25 | df['target'].loc[df['target']==2]=1 26 | return DataBlock(df,df,df,'target') 27 | -------------------------------------------------------------------------------- /easyML/tests/data_files/test.csv: -------------------------------------------------------------------------------- 1 | PassengerId,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked 2 | 892,3,"Kelly, Mr. James",male,34.5,0,0,330911,7.8292,,Q 3 | 893,3,"Wilkes, Mrs. James (Ellen Needs)",female,47,1,0,363272,7,,S 4 | 894,2,"Myles, Mr. Thomas Francis",male,62,0,0,240276,9.6875,,Q 5 | 895,3,"Wirz, Mr. Albert",male,27,0,0,315154,8.6625,,S 6 | 896,3,"Hirvonen, Mrs. Alexander (Helga E Lindqvist)",female,22,1,1,3101298,12.2875,,S 7 | 897,3,"Svensson, Mr. Johan Cervin",male,14,0,0,7538,9.225,,S 8 | 898,3,"Connolly, Miss. Kate",female,30,0,0,330972,7.6292,,Q 9 | 899,2,"Caldwell, Mr. Albert Francis",male,26,1,1,248738,29,,S 10 | 900,3,"Abrahim, Mrs. Joseph (Sophie Halaut Easu)",female,18,0,0,2657,7.2292,,C 11 | 901,3,"Davies, Mr. John Samuel",male,21,2,0,A/4 48871,24.15,,S 12 | 902,3,"Ilieff, Mr. Ylio",male,,0,0,349220,7.8958,,S 13 | 903,1,"Jones, Mr. Charles Cresson",male,46,0,0,694,26,,S 14 | 904,1,"Snyder, Mrs. John Pillsbury (Nelle Stevenson)",female,23,1,0,21228,82.2667,B45,S 15 | 905,2,"Howard, Mr. Benjamin",male,63,1,0,24065,26,,S 16 | 906,1,"Chaffee, Mrs. Herbert Fuller (Carrie Constance Toogood)",female,47,1,0,W.E.P. 5734,61.175,E31,S 17 | 907,2,"del Carlo, Mrs. Sebastiano (Argenia Genovesi)",female,24,1,0,SC/PARIS 2167,27.7208,,C 18 | 908,2,"Keane, Mr. Daniel",male,35,0,0,233734,12.35,,Q 19 | 909,3,"Assaf, Mr. Gerios",male,21,0,0,2692,7.225,,C 20 | 910,3,"Ilmakangas, Miss. Ida Livija",female,27,1,0,STON/O2. 3101270,7.925,,S 21 | 911,3,"Assaf Khalil, Mrs. Mariana (Miriam"")""",female,45,0,0,2696,7.225,,C 22 | 912,1,"Rothschild, Mr. Martin",male,55,1,0,PC 17603,59.4,,C 23 | 913,3,"Olsen, Master. Artur Karl",male,9,0,1,C 17368,3.1708,,S 24 | 914,1,"Flegenheim, Mrs. Alfred (Antoinette)",female,,0,0,PC 17598,31.6833,,S 25 | 915,1,"Williams, Mr. Richard Norris II",male,21,0,1,PC 17597,61.3792,,C 26 | 916,1,"Ryerson, Mrs. Arthur Larned (Emily Maria Borie)",female,48,1,3,PC 17608,262.375,B57 B59 B63 B66,C 27 | 917,3,"Robins, Mr. Alexander A",male,50,1,0,A/5. 3337,14.5,,S 28 | 918,1,"Ostby, Miss. Helene Ragnhild",female,22,0,1,113509,61.9792,B36,C 29 | 919,3,"Daher, Mr. Shedid",male,22.5,0,0,2698,7.225,,C 30 | 920,1,"Brady, Mr. John Bertram",male,41,0,0,113054,30.5,A21,S 31 | 921,3,"Samaan, Mr. Elias",male,,2,0,2662,21.6792,,C 32 | 922,2,"Louch, Mr. Charles Alexander",male,50,1,0,SC/AH 3085,26,,S 33 | 923,2,"Jefferys, Mr. Clifford Thomas",male,24,2,0,C.A. 31029,31.5,,S 34 | 924,3,"Dean, Mrs. Bertram (Eva Georgetta Light)",female,33,1,2,C.A. 2315,20.575,,S 35 | 925,3,"Johnston, Mrs. Andrew G (Elizabeth Lily"" Watson)""",female,,1,2,W./C. 6607,23.45,,S 36 | 926,1,"Mock, Mr. Philipp Edmund",male,30,1,0,13236,57.75,C78,C 37 | 927,3,"Katavelas, Mr. Vassilios (Catavelas Vassilios"")""",male,18.5,0,0,2682,7.2292,,C 38 | 928,3,"Roth, Miss. Sarah A",female,,0,0,342712,8.05,,S 39 | 929,3,"Cacic, Miss. Manda",female,21,0,0,315087,8.6625,,S 40 | 930,3,"Sap, Mr. Julius",male,25,0,0,345768,9.5,,S 41 | 931,3,"Hee, Mr. Ling",male,,0,0,1601,56.4958,,S 42 | 932,3,"Karun, Mr. Franz",male,39,0,1,349256,13.4167,,C 43 | 933,1,"Franklin, Mr. Thomas Parham",male,,0,0,113778,26.55,D34,S 44 | 934,3,"Goldsmith, Mr. Nathan",male,41,0,0,SOTON/O.Q. 3101263,7.85,,S 45 | 935,2,"Corbett, Mrs. Walter H (Irene Colvin)",female,30,0,0,237249,13,,S 46 | 936,1,"Kimball, Mrs. Edwin Nelson Jr (Gertrude Parsons)",female,45,1,0,11753,52.5542,D19,S 47 | 937,3,"Peltomaki, Mr. Nikolai Johannes",male,25,0,0,STON/O 2. 3101291,7.925,,S 48 | 938,1,"Chevre, Mr. Paul Romaine",male,45,0,0,PC 17594,29.7,A9,C 49 | 939,3,"Shaughnessy, Mr. Patrick",male,,0,0,370374,7.75,,Q 50 | 940,1,"Bucknell, Mrs. William Robert (Emma Eliza Ward)",female,60,0,0,11813,76.2917,D15,C 51 | 941,3,"Coutts, Mrs. William (Winnie Minnie"" Treanor)""",female,36,0,2,C.A. 37671,15.9,,S 52 | 942,1,"Smith, Mr. Lucien Philip",male,24,1,0,13695,60,C31,S 53 | 943,2,"Pulbaum, Mr. Franz",male,27,0,0,SC/PARIS 2168,15.0333,,C 54 | 944,2,"Hocking, Miss. Ellen Nellie""""",female,20,2,1,29105,23,,S 55 | 945,1,"Fortune, Miss. Ethel Flora",female,28,3,2,19950,263,C23 C25 C27,S 56 | 946,2,"Mangiavacchi, Mr. Serafino Emilio",male,,0,0,SC/A.3 2861,15.5792,,C 57 | 947,3,"Rice, Master. Albert",male,10,4,1,382652,29.125,,Q 58 | 948,3,"Cor, Mr. Bartol",male,35,0,0,349230,7.8958,,S 59 | 949,3,"Abelseth, Mr. Olaus Jorgensen",male,25,0,0,348122,7.65,F G63,S 60 | 950,3,"Davison, Mr. Thomas Henry",male,,1,0,386525,16.1,,S 61 | 951,1,"Chaudanson, Miss. Victorine",female,36,0,0,PC 17608,262.375,B61,C 62 | 952,3,"Dika, Mr. Mirko",male,17,0,0,349232,7.8958,,S 63 | 953,2,"McCrae, Mr. Arthur Gordon",male,32,0,0,237216,13.5,,S 64 | 954,3,"Bjorklund, Mr. Ernst Herbert",male,18,0,0,347090,7.75,,S 65 | 955,3,"Bradley, Miss. Bridget Delia",female,22,0,0,334914,7.725,,Q 66 | 956,1,"Ryerson, Master. John Borie",male,13,2,2,PC 17608,262.375,B57 B59 B63 B66,C 67 | 957,2,"Corey, Mrs. Percy C (Mary Phyllis Elizabeth Miller)",female,,0,0,F.C.C. 13534,21,,S 68 | 958,3,"Burns, Miss. Mary Delia",female,18,0,0,330963,7.8792,,Q 69 | 959,1,"Moore, Mr. Clarence Bloomfield",male,47,0,0,113796,42.4,,S 70 | 960,1,"Tucker, Mr. Gilbert Milligan Jr",male,31,0,0,2543,28.5375,C53,C 71 | 961,1,"Fortune, Mrs. Mark (Mary McDougald)",female,60,1,4,19950,263,C23 C25 C27,S 72 | 962,3,"Mulvihill, Miss. Bertha E",female,24,0,0,382653,7.75,,Q 73 | 963,3,"Minkoff, Mr. Lazar",male,21,0,0,349211,7.8958,,S 74 | 964,3,"Nieminen, Miss. Manta Josefina",female,29,0,0,3101297,7.925,,S 75 | 965,1,"Ovies y Rodriguez, Mr. Servando",male,28.5,0,0,PC 17562,27.7208,D43,C 76 | 966,1,"Geiger, Miss. Amalie",female,35,0,0,113503,211.5,C130,C 77 | 967,1,"Keeping, Mr. Edwin",male,32.5,0,0,113503,211.5,C132,C 78 | 968,3,"Miles, Mr. Frank",male,,0,0,359306,8.05,,S 79 | 969,1,"Cornell, Mrs. Robert Clifford (Malvina Helen Lamson)",female,55,2,0,11770,25.7,C101,S 80 | 970,2,"Aldworth, Mr. Charles Augustus",male,30,0,0,248744,13,,S 81 | 971,3,"Doyle, Miss. Elizabeth",female,24,0,0,368702,7.75,,Q 82 | 972,3,"Boulos, Master. Akar",male,6,1,1,2678,15.2458,,C 83 | 973,1,"Straus, Mr. Isidor",male,67,1,0,PC 17483,221.7792,C55 C57,S 84 | 974,1,"Case, Mr. Howard Brown",male,49,0,0,19924,26,,S 85 | 975,3,"Demetri, Mr. Marinko",male,,0,0,349238,7.8958,,S 86 | 976,2,"Lamb, Mr. John Joseph",male,,0,0,240261,10.7083,,Q 87 | 977,3,"Khalil, Mr. Betros",male,,1,0,2660,14.4542,,C 88 | 978,3,"Barry, Miss. Julia",female,27,0,0,330844,7.8792,,Q 89 | 979,3,"Badman, Miss. Emily Louisa",female,18,0,0,A/4 31416,8.05,,S 90 | 980,3,"O'Donoghue, Ms. Bridget",female,,0,0,364856,7.75,,Q 91 | 981,2,"Wells, Master. Ralph Lester",male,2,1,1,29103,23,,S 92 | 982,3,"Dyker, Mrs. Adolf Fredrik (Anna Elisabeth Judith Andersson)",female,22,1,0,347072,13.9,,S 93 | 983,3,"Pedersen, Mr. Olaf",male,,0,0,345498,7.775,,S 94 | 984,1,"Davidson, Mrs. Thornton (Orian Hays)",female,27,1,2,F.C. 12750,52,B71,S 95 | 985,3,"Guest, Mr. Robert",male,,0,0,376563,8.05,,S 96 | 986,1,"Birnbaum, Mr. Jakob",male,25,0,0,13905,26,,C 97 | 987,3,"Tenglin, Mr. Gunnar Isidor",male,25,0,0,350033,7.7958,,S 98 | 988,1,"Cavendish, Mrs. Tyrell William (Julia Florence Siegel)",female,76,1,0,19877,78.85,C46,S 99 | 989,3,"Makinen, Mr. Kalle Edvard",male,29,0,0,STON/O 2. 3101268,7.925,,S 100 | 990,3,"Braf, Miss. Elin Ester Maria",female,20,0,0,347471,7.8542,,S 101 | 991,3,"Nancarrow, Mr. William Henry",male,33,0,0,A./5. 3338,8.05,,S 102 | 992,1,"Stengel, Mrs. Charles Emil Henry (Annie May Morris)",female,43,1,0,11778,55.4417,C116,C 103 | 993,2,"Weisz, Mr. Leopold",male,27,1,0,228414,26,,S 104 | 994,3,"Foley, Mr. William",male,,0,0,365235,7.75,,Q 105 | 995,3,"Johansson Palmquist, Mr. Oskar Leander",male,26,0,0,347070,7.775,,S 106 | 996,3,"Thomas, Mrs. Alexander (Thamine Thelma"")""",female,16,1,1,2625,8.5167,,C 107 | 997,3,"Holthen, Mr. Johan Martin",male,28,0,0,C 4001,22.525,,S 108 | 998,3,"Buckley, Mr. Daniel",male,21,0,0,330920,7.8208,,Q 109 | 999,3,"Ryan, Mr. Edward",male,,0,0,383162,7.75,,Q 110 | 1000,3,"Willer, Mr. Aaron (Abi Weller"")""",male,,0,0,3410,8.7125,,S 111 | 1001,2,"Swane, Mr. George",male,18.5,0,0,248734,13,F,S 112 | 1002,2,"Stanton, Mr. Samuel Ward",male,41,0,0,237734,15.0458,,C 113 | 1003,3,"Shine, Miss. Ellen Natalia",female,,0,0,330968,7.7792,,Q 114 | 1004,1,"Evans, Miss. Edith Corse",female,36,0,0,PC 17531,31.6792,A29,C 115 | 1005,3,"Buckley, Miss. Katherine",female,18.5,0,0,329944,7.2833,,Q 116 | 1006,1,"Straus, Mrs. Isidor (Rosalie Ida Blun)",female,63,1,0,PC 17483,221.7792,C55 C57,S 117 | 1007,3,"Chronopoulos, Mr. Demetrios",male,18,1,0,2680,14.4542,,C 118 | 1008,3,"Thomas, Mr. John",male,,0,0,2681,6.4375,,C 119 | 1009,3,"Sandstrom, Miss. Beatrice Irene",female,1,1,1,PP 9549,16.7,G6,S 120 | 1010,1,"Beattie, Mr. Thomson",male,36,0,0,13050,75.2417,C6,C 121 | 1011,2,"Chapman, Mrs. John Henry (Sara Elizabeth Lawry)",female,29,1,0,SC/AH 29037,26,,S 122 | 1012,2,"Watt, Miss. Bertha J",female,12,0,0,C.A. 33595,15.75,,S 123 | 1013,3,"Kiernan, Mr. John",male,,1,0,367227,7.75,,Q 124 | 1014,1,"Schabert, Mrs. Paul (Emma Mock)",female,35,1,0,13236,57.75,C28,C 125 | 1015,3,"Carver, Mr. Alfred John",male,28,0,0,392095,7.25,,S 126 | 1016,3,"Kennedy, Mr. John",male,,0,0,368783,7.75,,Q 127 | 1017,3,"Cribb, Miss. Laura Alice",female,17,0,1,371362,16.1,,S 128 | 1018,3,"Brobeck, Mr. Karl Rudolf",male,22,0,0,350045,7.7958,,S 129 | 1019,3,"McCoy, Miss. Alicia",female,,2,0,367226,23.25,,Q 130 | 1020,2,"Bowenur, Mr. Solomon",male,42,0,0,211535,13,,S 131 | 1021,3,"Petersen, Mr. Marius",male,24,0,0,342441,8.05,,S 132 | 1022,3,"Spinner, Mr. Henry John",male,32,0,0,STON/OQ. 369943,8.05,,S 133 | 1023,1,"Gracie, Col. Archibald IV",male,53,0,0,113780,28.5,C51,C 134 | 1024,3,"Lefebre, Mrs. Frank (Frances)",female,,0,4,4133,25.4667,,S 135 | 1025,3,"Thomas, Mr. Charles P",male,,1,0,2621,6.4375,,C 136 | 1026,3,"Dintcheff, Mr. Valtcho",male,43,0,0,349226,7.8958,,S 137 | 1027,3,"Carlsson, Mr. Carl Robert",male,24,0,0,350409,7.8542,,S 138 | 1028,3,"Zakarian, Mr. Mapriededer",male,26.5,0,0,2656,7.225,,C 139 | 1029,2,"Schmidt, Mr. August",male,26,0,0,248659,13,,S 140 | 1030,3,"Drapkin, Miss. Jennie",female,23,0,0,SOTON/OQ 392083,8.05,,S 141 | 1031,3,"Goodwin, Mr. Charles Frederick",male,40,1,6,CA 2144,46.9,,S 142 | 1032,3,"Goodwin, Miss. Jessie Allis",female,10,5,2,CA 2144,46.9,,S 143 | 1033,1,"Daniels, Miss. Sarah",female,33,0,0,113781,151.55,,S 144 | 1034,1,"Ryerson, Mr. Arthur Larned",male,61,1,3,PC 17608,262.375,B57 B59 B63 B66,C 145 | 1035,2,"Beauchamp, Mr. Henry James",male,28,0,0,244358,26,,S 146 | 1036,1,"Lindeberg-Lind, Mr. Erik Gustaf (Mr Edward Lingrey"")""",male,42,0,0,17475,26.55,,S 147 | 1037,3,"Vander Planke, Mr. Julius",male,31,3,0,345763,18,,S 148 | 1038,1,"Hilliard, Mr. Herbert Henry",male,,0,0,17463,51.8625,E46,S 149 | 1039,3,"Davies, Mr. Evan",male,22,0,0,SC/A4 23568,8.05,,S 150 | 1040,1,"Crafton, Mr. John Bertram",male,,0,0,113791,26.55,,S 151 | 1041,2,"Lahtinen, Rev. William",male,30,1,1,250651,26,,S 152 | 1042,1,"Earnshaw, Mrs. Boulton (Olive Potter)",female,23,0,1,11767,83.1583,C54,C 153 | 1043,3,"Matinoff, Mr. Nicola",male,,0,0,349255,7.8958,,C 154 | 1044,3,"Storey, Mr. Thomas",male,60.5,0,0,3701,,,S 155 | 1045,3,"Klasen, Mrs. (Hulda Kristina Eugenia Lofqvist)",female,36,0,2,350405,12.1833,,S 156 | 1046,3,"Asplund, Master. Filip Oscar",male,13,4,2,347077,31.3875,,S 157 | 1047,3,"Duquemin, Mr. Joseph",male,24,0,0,S.O./P.P. 752,7.55,,S 158 | 1048,1,"Bird, Miss. Ellen",female,29,0,0,PC 17483,221.7792,C97,S 159 | 1049,3,"Lundin, Miss. Olga Elida",female,23,0,0,347469,7.8542,,S 160 | 1050,1,"Borebank, Mr. John James",male,42,0,0,110489,26.55,D22,S 161 | 1051,3,"Peacock, Mrs. Benjamin (Edith Nile)",female,26,0,2,SOTON/O.Q. 3101315,13.775,,S 162 | 1052,3,"Smyth, Miss. Julia",female,,0,0,335432,7.7333,,Q 163 | 1053,3,"Touma, Master. Georges Youssef",male,7,1,1,2650,15.2458,,C 164 | 1054,2,"Wright, Miss. Marion",female,26,0,0,220844,13.5,,S 165 | 1055,3,"Pearce, Mr. Ernest",male,,0,0,343271,7,,S 166 | 1056,2,"Peruschitz, Rev. Joseph Maria",male,41,0,0,237393,13,,S 167 | 1057,3,"Kink-Heilmann, Mrs. Anton (Luise Heilmann)",female,26,1,1,315153,22.025,,S 168 | 1058,1,"Brandeis, Mr. Emil",male,48,0,0,PC 17591,50.4958,B10,C 169 | 1059,3,"Ford, Mr. Edward Watson",male,18,2,2,W./C. 6608,34.375,,S 170 | 1060,1,"Cassebeer, Mrs. Henry Arthur Jr (Eleanor Genevieve Fosdick)",female,,0,0,17770,27.7208,,C 171 | 1061,3,"Hellstrom, Miss. Hilda Maria",female,22,0,0,7548,8.9625,,S 172 | 1062,3,"Lithman, Mr. Simon",male,,0,0,S.O./P.P. 251,7.55,,S 173 | 1063,3,"Zakarian, Mr. Ortin",male,27,0,0,2670,7.225,,C 174 | 1064,3,"Dyker, Mr. Adolf Fredrik",male,23,1,0,347072,13.9,,S 175 | 1065,3,"Torfa, Mr. Assad",male,,0,0,2673,7.2292,,C 176 | 1066,3,"Asplund, Mr. Carl Oscar Vilhelm Gustafsson",male,40,1,5,347077,31.3875,,S 177 | 1067,2,"Brown, Miss. Edith Eileen",female,15,0,2,29750,39,,S 178 | 1068,2,"Sincock, Miss. Maude",female,20,0,0,C.A. 33112,36.75,,S 179 | 1069,1,"Stengel, Mr. Charles Emil Henry",male,54,1,0,11778,55.4417,C116,C 180 | 1070,2,"Becker, Mrs. Allen Oliver (Nellie E Baumgardner)",female,36,0,3,230136,39,F4,S 181 | 1071,1,"Compton, Mrs. Alexander Taylor (Mary Eliza Ingersoll)",female,64,0,2,PC 17756,83.1583,E45,C 182 | 1072,2,"McCrie, Mr. James Matthew",male,30,0,0,233478,13,,S 183 | 1073,1,"Compton, Mr. Alexander Taylor Jr",male,37,1,1,PC 17756,83.1583,E52,C 184 | 1074,1,"Marvin, Mrs. Daniel Warner (Mary Graham Carmichael Farquarson)",female,18,1,0,113773,53.1,D30,S 185 | 1075,3,"Lane, Mr. Patrick",male,,0,0,7935,7.75,,Q 186 | 1076,1,"Douglas, Mrs. Frederick Charles (Mary Helene Baxter)",female,27,1,1,PC 17558,247.5208,B58 B60,C 187 | 1077,2,"Maybery, Mr. Frank Hubert",male,40,0,0,239059,16,,S 188 | 1078,2,"Phillips, Miss. Alice Frances Louisa",female,21,0,1,S.O./P.P. 2,21,,S 189 | 1079,3,"Davies, Mr. Joseph",male,17,2,0,A/4 48873,8.05,,S 190 | 1080,3,"Sage, Miss. Ada",female,,8,2,CA. 2343,69.55,,S 191 | 1081,2,"Veal, Mr. James",male,40,0,0,28221,13,,S 192 | 1082,2,"Angle, Mr. William A",male,34,1,0,226875,26,,S 193 | 1083,1,"Salomon, Mr. Abraham L",male,,0,0,111163,26,,S 194 | 1084,3,"van Billiard, Master. Walter John",male,11.5,1,1,A/5. 851,14.5,,S 195 | 1085,2,"Lingane, Mr. John",male,61,0,0,235509,12.35,,Q 196 | 1086,2,"Drew, Master. Marshall Brines",male,8,0,2,28220,32.5,,S 197 | 1087,3,"Karlsson, Mr. Julius Konrad Eugen",male,33,0,0,347465,7.8542,,S 198 | 1088,1,"Spedden, Master. Robert Douglas",male,6,0,2,16966,134.5,E34,C 199 | 1089,3,"Nilsson, Miss. Berta Olivia",female,18,0,0,347066,7.775,,S 200 | 1090,2,"Baimbrigge, Mr. Charles Robert",male,23,0,0,C.A. 31030,10.5,,S 201 | 1091,3,"Rasmussen, Mrs. (Lena Jacobsen Solvang)",female,,0,0,65305,8.1125,,S 202 | 1092,3,"Murphy, Miss. Nora",female,,0,0,36568,15.5,,Q 203 | 1093,3,"Danbom, Master. Gilbert Sigvard Emanuel",male,0.33,0,2,347080,14.4,,S 204 | 1094,1,"Astor, Col. John Jacob",male,47,1,0,PC 17757,227.525,C62 C64,C 205 | 1095,2,"Quick, Miss. Winifred Vera",female,8,1,1,26360,26,,S 206 | 1096,2,"Andrew, Mr. Frank Thomas",male,25,0,0,C.A. 34050,10.5,,S 207 | 1097,1,"Omont, Mr. Alfred Fernand",male,,0,0,F.C. 12998,25.7417,,C 208 | 1098,3,"McGowan, Miss. Katherine",female,35,0,0,9232,7.75,,Q 209 | 1099,2,"Collett, Mr. Sidney C Stuart",male,24,0,0,28034,10.5,,S 210 | 1100,1,"Rosenbaum, Miss. Edith Louise",female,33,0,0,PC 17613,27.7208,A11,C 211 | 1101,3,"Delalic, Mr. Redjo",male,25,0,0,349250,7.8958,,S 212 | 1102,3,"Andersen, Mr. Albert Karvin",male,32,0,0,C 4001,22.525,,S 213 | 1103,3,"Finoli, Mr. Luigi",male,,0,0,SOTON/O.Q. 3101308,7.05,,S 214 | 1104,2,"Deacon, Mr. Percy William",male,17,0,0,S.O.C. 14879,73.5,,S 215 | 1105,2,"Howard, Mrs. Benjamin (Ellen Truelove Arman)",female,60,1,0,24065,26,,S 216 | 1106,3,"Andersson, Miss. Ida Augusta Margareta",female,38,4,2,347091,7.775,,S 217 | 1107,1,"Head, Mr. Christopher",male,42,0,0,113038,42.5,B11,S 218 | 1108,3,"Mahon, Miss. Bridget Delia",female,,0,0,330924,7.8792,,Q 219 | 1109,1,"Wick, Mr. George Dennick",male,57,1,1,36928,164.8667,,S 220 | 1110,1,"Widener, Mrs. George Dunton (Eleanor Elkins)",female,50,1,1,113503,211.5,C80,C 221 | 1111,3,"Thomson, Mr. Alexander Morrison",male,,0,0,32302,8.05,,S 222 | 1112,2,"Duran y More, Miss. Florentina",female,30,1,0,SC/PARIS 2148,13.8583,,C 223 | 1113,3,"Reynolds, Mr. Harold J",male,21,0,0,342684,8.05,,S 224 | 1114,2,"Cook, Mrs. (Selena Rogers)",female,22,0,0,W./C. 14266,10.5,F33,S 225 | 1115,3,"Karlsson, Mr. Einar Gervasius",male,21,0,0,350053,7.7958,,S 226 | 1116,1,"Candee, Mrs. Edward (Helen Churchill Hungerford)",female,53,0,0,PC 17606,27.4458,,C 227 | 1117,3,"Moubarek, Mrs. George (Omine Amenia"" Alexander)""",female,,0,2,2661,15.2458,,C 228 | 1118,3,"Asplund, Mr. Johan Charles",male,23,0,0,350054,7.7958,,S 229 | 1119,3,"McNeill, Miss. Bridget",female,,0,0,370368,7.75,,Q 230 | 1120,3,"Everett, Mr. Thomas James",male,40.5,0,0,C.A. 6212,15.1,,S 231 | 1121,2,"Hocking, Mr. Samuel James Metcalfe",male,36,0,0,242963,13,,S 232 | 1122,2,"Sweet, Mr. George Frederick",male,14,0,0,220845,65,,S 233 | 1123,1,"Willard, Miss. Constance",female,21,0,0,113795,26.55,,S 234 | 1124,3,"Wiklund, Mr. Karl Johan",male,21,1,0,3101266,6.4958,,S 235 | 1125,3,"Linehan, Mr. Michael",male,,0,0,330971,7.8792,,Q 236 | 1126,1,"Cumings, Mr. John Bradley",male,39,1,0,PC 17599,71.2833,C85,C 237 | 1127,3,"Vendel, Mr. Olof Edvin",male,20,0,0,350416,7.8542,,S 238 | 1128,1,"Warren, Mr. Frank Manley",male,64,1,0,110813,75.25,D37,C 239 | 1129,3,"Baccos, Mr. Raffull",male,20,0,0,2679,7.225,,C 240 | 1130,2,"Hiltunen, Miss. Marta",female,18,1,1,250650,13,,S 241 | 1131,1,"Douglas, Mrs. Walter Donald (Mahala Dutton)",female,48,1,0,PC 17761,106.425,C86,C 242 | 1132,1,"Lindstrom, Mrs. Carl Johan (Sigrid Posse)",female,55,0,0,112377,27.7208,,C 243 | 1133,2,"Christy, Mrs. (Alice Frances)",female,45,0,2,237789,30,,S 244 | 1134,1,"Spedden, Mr. Frederic Oakley",male,45,1,1,16966,134.5,E34,C 245 | 1135,3,"Hyman, Mr. Abraham",male,,0,0,3470,7.8875,,S 246 | 1136,3,"Johnston, Master. William Arthur Willie""""",male,,1,2,W./C. 6607,23.45,,S 247 | 1137,1,"Kenyon, Mr. Frederick R",male,41,1,0,17464,51.8625,D21,S 248 | 1138,2,"Karnes, Mrs. J Frank (Claire Bennett)",female,22,0,0,F.C.C. 13534,21,,S 249 | 1139,2,"Drew, Mr. James Vivian",male,42,1,1,28220,32.5,,S 250 | 1140,2,"Hold, Mrs. Stephen (Annie Margaret Hill)",female,29,1,0,26707,26,,S 251 | 1141,3,"Khalil, Mrs. Betros (Zahie Maria"" Elias)""",female,,1,0,2660,14.4542,,C 252 | 1142,2,"West, Miss. Barbara J",female,0.92,1,2,C.A. 34651,27.75,,S 253 | 1143,3,"Abrahamsson, Mr. Abraham August Johannes",male,20,0,0,SOTON/O2 3101284,7.925,,S 254 | 1144,1,"Clark, Mr. Walter Miller",male,27,1,0,13508,136.7792,C89,C 255 | 1145,3,"Salander, Mr. Karl Johan",male,24,0,0,7266,9.325,,S 256 | 1146,3,"Wenzel, Mr. Linhart",male,32.5,0,0,345775,9.5,,S 257 | 1147,3,"MacKay, Mr. George William",male,,0,0,C.A. 42795,7.55,,S 258 | 1148,3,"Mahon, Mr. John",male,,0,0,AQ/4 3130,7.75,,Q 259 | 1149,3,"Niklasson, Mr. Samuel",male,28,0,0,363611,8.05,,S 260 | 1150,2,"Bentham, Miss. Lilian W",female,19,0,0,28404,13,,S 261 | 1151,3,"Midtsjo, Mr. Karl Albert",male,21,0,0,345501,7.775,,S 262 | 1152,3,"de Messemaeker, Mr. Guillaume Joseph",male,36.5,1,0,345572,17.4,,S 263 | 1153,3,"Nilsson, Mr. August Ferdinand",male,21,0,0,350410,7.8542,,S 264 | 1154,2,"Wells, Mrs. Arthur Henry (Addie"" Dart Trevaskis)""",female,29,0,2,29103,23,,S 265 | 1155,3,"Klasen, Miss. Gertrud Emilia",female,1,1,1,350405,12.1833,,S 266 | 1156,2,"Portaluppi, Mr. Emilio Ilario Giuseppe",male,30,0,0,C.A. 34644,12.7375,,C 267 | 1157,3,"Lyntakoff, Mr. Stanko",male,,0,0,349235,7.8958,,S 268 | 1158,1,"Chisholm, Mr. Roderick Robert Crispin",male,,0,0,112051,0,,S 269 | 1159,3,"Warren, Mr. Charles William",male,,0,0,C.A. 49867,7.55,,S 270 | 1160,3,"Howard, Miss. May Elizabeth",female,,0,0,A. 2. 39186,8.05,,S 271 | 1161,3,"Pokrnic, Mr. Mate",male,17,0,0,315095,8.6625,,S 272 | 1162,1,"McCaffry, Mr. Thomas Francis",male,46,0,0,13050,75.2417,C6,C 273 | 1163,3,"Fox, Mr. Patrick",male,,0,0,368573,7.75,,Q 274 | 1164,1,"Clark, Mrs. Walter Miller (Virginia McDowell)",female,26,1,0,13508,136.7792,C89,C 275 | 1165,3,"Lennon, Miss. Mary",female,,1,0,370371,15.5,,Q 276 | 1166,3,"Saade, Mr. Jean Nassr",male,,0,0,2676,7.225,,C 277 | 1167,2,"Bryhl, Miss. Dagmar Jenny Ingeborg ",female,20,1,0,236853,26,,S 278 | 1168,2,"Parker, Mr. Clifford Richard",male,28,0,0,SC 14888,10.5,,S 279 | 1169,2,"Faunthorpe, Mr. Harry",male,40,1,0,2926,26,,S 280 | 1170,2,"Ware, Mr. John James",male,30,1,0,CA 31352,21,,S 281 | 1171,2,"Oxenham, Mr. Percy Thomas",male,22,0,0,W./C. 14260,10.5,,S 282 | 1172,3,"Oreskovic, Miss. Jelka",female,23,0,0,315085,8.6625,,S 283 | 1173,3,"Peacock, Master. Alfred Edward",male,0.75,1,1,SOTON/O.Q. 3101315,13.775,,S 284 | 1174,3,"Fleming, Miss. Honora",female,,0,0,364859,7.75,,Q 285 | 1175,3,"Touma, Miss. Maria Youssef",female,9,1,1,2650,15.2458,,C 286 | 1176,3,"Rosblom, Miss. Salli Helena",female,2,1,1,370129,20.2125,,S 287 | 1177,3,"Dennis, Mr. William",male,36,0,0,A/5 21175,7.25,,S 288 | 1178,3,"Franklin, Mr. Charles (Charles Fardon)",male,,0,0,SOTON/O.Q. 3101314,7.25,,S 289 | 1179,1,"Snyder, Mr. John Pillsbury",male,24,1,0,21228,82.2667,B45,S 290 | 1180,3,"Mardirosian, Mr. Sarkis",male,,0,0,2655,7.2292,F E46,C 291 | 1181,3,"Ford, Mr. Arthur",male,,0,0,A/5 1478,8.05,,S 292 | 1182,1,"Rheims, Mr. George Alexander Lucien",male,,0,0,PC 17607,39.6,,S 293 | 1183,3,"Daly, Miss. Margaret Marcella Maggie""""",female,30,0,0,382650,6.95,,Q 294 | 1184,3,"Nasr, Mr. Mustafa",male,,0,0,2652,7.2292,,C 295 | 1185,1,"Dodge, Dr. Washington",male,53,1,1,33638,81.8583,A34,S 296 | 1186,3,"Wittevrongel, Mr. Camille",male,36,0,0,345771,9.5,,S 297 | 1187,3,"Angheloff, Mr. Minko",male,26,0,0,349202,7.8958,,S 298 | 1188,2,"Laroche, Miss. Louise",female,1,1,2,SC/Paris 2123,41.5792,,C 299 | 1189,3,"Samaan, Mr. Hanna",male,,2,0,2662,21.6792,,C 300 | 1190,1,"Loring, Mr. Joseph Holland",male,30,0,0,113801,45.5,,S 301 | 1191,3,"Johansson, Mr. Nils",male,29,0,0,347467,7.8542,,S 302 | 1192,3,"Olsson, Mr. Oscar Wilhelm",male,32,0,0,347079,7.775,,S 303 | 1193,2,"Malachard, Mr. Noel",male,,0,0,237735,15.0458,D,C 304 | 1194,2,"Phillips, Mr. Escott Robert",male,43,0,1,S.O./P.P. 2,21,,S 305 | 1195,3,"Pokrnic, Mr. Tome",male,24,0,0,315092,8.6625,,S 306 | 1196,3,"McCarthy, Miss. Catherine Katie""""",female,,0,0,383123,7.75,,Q 307 | 1197,1,"Crosby, Mrs. Edward Gifford (Catherine Elizabeth Halstead)",female,64,1,1,112901,26.55,B26,S 308 | 1198,1,"Allison, Mr. Hudson Joshua Creighton",male,30,1,2,113781,151.55,C22 C26,S 309 | 1199,3,"Aks, Master. Philip Frank",male,0.83,0,1,392091,9.35,,S 310 | 1200,1,"Hays, Mr. Charles Melville",male,55,1,1,12749,93.5,B69,S 311 | 1201,3,"Hansen, Mrs. Claus Peter (Jennie L Howard)",female,45,1,0,350026,14.1083,,S 312 | 1202,3,"Cacic, Mr. Jego Grga",male,18,0,0,315091,8.6625,,S 313 | 1203,3,"Vartanian, Mr. David",male,22,0,0,2658,7.225,,C 314 | 1204,3,"Sadowitz, Mr. Harry",male,,0,0,LP 1588,7.575,,S 315 | 1205,3,"Carr, Miss. Jeannie",female,37,0,0,368364,7.75,,Q 316 | 1206,1,"White, Mrs. John Stuart (Ella Holmes)",female,55,0,0,PC 17760,135.6333,C32,C 317 | 1207,3,"Hagardon, Miss. Kate",female,17,0,0,AQ/3. 30631,7.7333,,Q 318 | 1208,1,"Spencer, Mr. William Augustus",male,57,1,0,PC 17569,146.5208,B78,C 319 | 1209,2,"Rogers, Mr. Reginald Harry",male,19,0,0,28004,10.5,,S 320 | 1210,3,"Jonsson, Mr. Nils Hilding",male,27,0,0,350408,7.8542,,S 321 | 1211,2,"Jefferys, Mr. Ernest Wilfred",male,22,2,0,C.A. 31029,31.5,,S 322 | 1212,3,"Andersson, Mr. Johan Samuel",male,26,0,0,347075,7.775,,S 323 | 1213,3,"Krekorian, Mr. Neshan",male,25,0,0,2654,7.2292,F E57,C 324 | 1214,2,"Nesson, Mr. Israel",male,26,0,0,244368,13,F2,S 325 | 1215,1,"Rowe, Mr. Alfred G",male,33,0,0,113790,26.55,,S 326 | 1216,1,"Kreuchen, Miss. Emilie",female,39,0,0,24160,211.3375,,S 327 | 1217,3,"Assam, Mr. Ali",male,23,0,0,SOTON/O.Q. 3101309,7.05,,S 328 | 1218,2,"Becker, Miss. Ruth Elizabeth",female,12,2,1,230136,39,F4,S 329 | 1219,1,"Rosenshine, Mr. George (Mr George Thorne"")""",male,46,0,0,PC 17585,79.2,,C 330 | 1220,2,"Clarke, Mr. Charles Valentine",male,29,1,0,2003,26,,S 331 | 1221,2,"Enander, Mr. Ingvar",male,21,0,0,236854,13,,S 332 | 1222,2,"Davies, Mrs. John Morgan (Elizabeth Agnes Mary White) ",female,48,0,2,C.A. 33112,36.75,,S 333 | 1223,1,"Dulles, Mr. William Crothers",male,39,0,0,PC 17580,29.7,A18,C 334 | 1224,3,"Thomas, Mr. Tannous",male,,0,0,2684,7.225,,C 335 | 1225,3,"Nakid, Mrs. Said (Waika Mary"" Mowad)""",female,19,1,1,2653,15.7417,,C 336 | 1226,3,"Cor, Mr. Ivan",male,27,0,0,349229,7.8958,,S 337 | 1227,1,"Maguire, Mr. John Edward",male,30,0,0,110469,26,C106,S 338 | 1228,2,"de Brito, Mr. Jose Joaquim",male,32,0,0,244360,13,,S 339 | 1229,3,"Elias, Mr. Joseph",male,39,0,2,2675,7.2292,,C 340 | 1230,2,"Denbury, Mr. Herbert",male,25,0,0,C.A. 31029,31.5,,S 341 | 1231,3,"Betros, Master. Seman",male,,0,0,2622,7.2292,,C 342 | 1232,2,"Fillbrook, Mr. Joseph Charles",male,18,0,0,C.A. 15185,10.5,,S 343 | 1233,3,"Lundstrom, Mr. Thure Edvin",male,32,0,0,350403,7.5792,,S 344 | 1234,3,"Sage, Mr. John George",male,,1,9,CA. 2343,69.55,,S 345 | 1235,1,"Cardeza, Mrs. James Warburton Martinez (Charlotte Wardle Drake)",female,58,0,1,PC 17755,512.3292,B51 B53 B55,C 346 | 1236,3,"van Billiard, Master. James William",male,,1,1,A/5. 851,14.5,,S 347 | 1237,3,"Abelseth, Miss. Karen Marie",female,16,0,0,348125,7.65,,S 348 | 1238,2,"Botsford, Mr. William Hull",male,26,0,0,237670,13,,S 349 | 1239,3,"Whabee, Mrs. George Joseph (Shawneene Abi-Saab)",female,38,0,0,2688,7.2292,,C 350 | 1240,2,"Giles, Mr. Ralph",male,24,0,0,248726,13.5,,S 351 | 1241,2,"Walcroft, Miss. Nellie",female,31,0,0,F.C.C. 13528,21,,S 352 | 1242,1,"Greenfield, Mrs. Leo David (Blanche Strouse)",female,45,0,1,PC 17759,63.3583,D10 D12,C 353 | 1243,2,"Stokes, Mr. Philip Joseph",male,25,0,0,F.C.C. 13540,10.5,,S 354 | 1244,2,"Dibden, Mr. William",male,18,0,0,S.O.C. 14879,73.5,,S 355 | 1245,2,"Herman, Mr. Samuel",male,49,1,2,220845,65,,S 356 | 1246,3,"Dean, Miss. Elizabeth Gladys Millvina""""",female,0.17,1,2,C.A. 2315,20.575,,S 357 | 1247,1,"Julian, Mr. Henry Forbes",male,50,0,0,113044,26,E60,S 358 | 1248,1,"Brown, Mrs. John Murray (Caroline Lane Lamson)",female,59,2,0,11769,51.4792,C101,S 359 | 1249,3,"Lockyer, Mr. Edward",male,,0,0,1222,7.8792,,S 360 | 1250,3,"O'Keefe, Mr. Patrick",male,,0,0,368402,7.75,,Q 361 | 1251,3,"Lindell, Mrs. Edvard Bengtsson (Elin Gerda Persson)",female,30,1,0,349910,15.55,,S 362 | 1252,3,"Sage, Master. William Henry",male,14.5,8,2,CA. 2343,69.55,,S 363 | 1253,2,"Mallet, Mrs. Albert (Antoinette Magnin)",female,24,1,1,S.C./PARIS 2079,37.0042,,C 364 | 1254,2,"Ware, Mrs. John James (Florence Louise Long)",female,31,0,0,CA 31352,21,,S 365 | 1255,3,"Strilic, Mr. Ivan",male,27,0,0,315083,8.6625,,S 366 | 1256,1,"Harder, Mrs. George Achilles (Dorothy Annan)",female,25,1,0,11765,55.4417,E50,C 367 | 1257,3,"Sage, Mrs. John (Annie Bullen)",female,,1,9,CA. 2343,69.55,,S 368 | 1258,3,"Caram, Mr. Joseph",male,,1,0,2689,14.4583,,C 369 | 1259,3,"Riihivouri, Miss. Susanna Juhantytar Sanni""""",female,22,0,0,3101295,39.6875,,S 370 | 1260,1,"Gibson, Mrs. Leonard (Pauline C Boeson)",female,45,0,1,112378,59.4,,C 371 | 1261,2,"Pallas y Castello, Mr. Emilio",male,29,0,0,SC/PARIS 2147,13.8583,,C 372 | 1262,2,"Giles, Mr. Edgar",male,21,1,0,28133,11.5,,S 373 | 1263,1,"Wilson, Miss. Helen Alice",female,31,0,0,16966,134.5,E39 E41,C 374 | 1264,1,"Ismay, Mr. Joseph Bruce",male,49,0,0,112058,0,B52 B54 B56,S 375 | 1265,2,"Harbeck, Mr. William H",male,44,0,0,248746,13,,S 376 | 1266,1,"Dodge, Mrs. Washington (Ruth Vidaver)",female,54,1,1,33638,81.8583,A34,S 377 | 1267,1,"Bowen, Miss. Grace Scott",female,45,0,0,PC 17608,262.375,,C 378 | 1268,3,"Kink, Miss. Maria",female,22,2,0,315152,8.6625,,S 379 | 1269,2,"Cotterill, Mr. Henry Harry""""",male,21,0,0,29107,11.5,,S 380 | 1270,1,"Hipkins, Mr. William Edward",male,55,0,0,680,50,C39,S 381 | 1271,3,"Asplund, Master. Carl Edgar",male,5,4,2,347077,31.3875,,S 382 | 1272,3,"O'Connor, Mr. Patrick",male,,0,0,366713,7.75,,Q 383 | 1273,3,"Foley, Mr. Joseph",male,26,0,0,330910,7.8792,,Q 384 | 1274,3,"Risien, Mrs. Samuel (Emma)",female,,0,0,364498,14.5,,S 385 | 1275,3,"McNamee, Mrs. Neal (Eileen O'Leary)",female,19,1,0,376566,16.1,,S 386 | 1276,2,"Wheeler, Mr. Edwin Frederick""""",male,,0,0,SC/PARIS 2159,12.875,,S 387 | 1277,2,"Herman, Miss. Kate",female,24,1,2,220845,65,,S 388 | 1278,3,"Aronsson, Mr. Ernst Axel Algot",male,24,0,0,349911,7.775,,S 389 | 1279,2,"Ashby, Mr. John",male,57,0,0,244346,13,,S 390 | 1280,3,"Canavan, Mr. Patrick",male,21,0,0,364858,7.75,,Q 391 | 1281,3,"Palsson, Master. Paul Folke",male,6,3,1,349909,21.075,,S 392 | 1282,1,"Payne, Mr. Vivian Ponsonby",male,23,0,0,12749,93.5,B24,S 393 | 1283,1,"Lines, Mrs. Ernest H (Elizabeth Lindsey James)",female,51,0,1,PC 17592,39.4,D28,S 394 | 1284,3,"Abbott, Master. Eugene Joseph",male,13,0,2,C.A. 2673,20.25,,S 395 | 1285,2,"Gilbert, Mr. William",male,47,0,0,C.A. 30769,10.5,,S 396 | 1286,3,"Kink-Heilmann, Mr. Anton",male,29,3,1,315153,22.025,,S 397 | 1287,1,"Smith, Mrs. Lucien Philip (Mary Eloise Hughes)",female,18,1,0,13695,60,C31,S 398 | 1288,3,"Colbert, Mr. Patrick",male,24,0,0,371109,7.25,,Q 399 | 1289,1,"Frolicher-Stehli, Mrs. Maxmillian (Margaretha Emerentia Stehli)",female,48,1,1,13567,79.2,B41,C 400 | 1290,3,"Larsson-Rondberg, Mr. Edvard A",male,22,0,0,347065,7.775,,S 401 | 1291,3,"Conlon, Mr. Thomas Henry",male,31,0,0,21332,7.7333,,Q 402 | 1292,1,"Bonnell, Miss. Caroline",female,30,0,0,36928,164.8667,C7,S 403 | 1293,2,"Gale, Mr. Harry",male,38,1,0,28664,21,,S 404 | 1294,1,"Gibson, Miss. Dorothy Winifred",female,22,0,1,112378,59.4,,C 405 | 1295,1,"Carrau, Mr. Jose Pedro",male,17,0,0,113059,47.1,,S 406 | 1296,1,"Frauenthal, Mr. Isaac Gerald",male,43,1,0,17765,27.7208,D40,C 407 | 1297,2,"Nourney, Mr. Alfred (Baron von Drachstedt"")""",male,20,0,0,SC/PARIS 2166,13.8625,D38,C 408 | 1298,2,"Ware, Mr. William Jeffery",male,23,1,0,28666,10.5,,S 409 | 1299,1,"Widener, Mr. George Dunton",male,50,1,1,113503,211.5,C80,C 410 | 1300,3,"Riordan, Miss. Johanna Hannah""""",female,,0,0,334915,7.7208,,Q 411 | 1301,3,"Peacock, Miss. Treasteall",female,3,1,1,SOTON/O.Q. 3101315,13.775,,S 412 | 1302,3,"Naughton, Miss. Hannah",female,,0,0,365237,7.75,,Q 413 | 1303,1,"Minahan, Mrs. William Edward (Lillian E Thorpe)",female,37,1,0,19928,90,C78,Q 414 | 1304,3,"Henriksson, Miss. Jenny Lovisa",female,28,0,0,347086,7.775,,S 415 | 1305,3,"Spector, Mr. Woolf",male,,0,0,A.5. 3236,8.05,,S 416 | 1306,1,"Oliva y Ocana, Dona. Fermina",female,39,0,0,PC 17758,108.9,C105,C 417 | 1307,3,"Saether, Mr. Simon Sivertsen",male,38.5,0,0,SOTON/O.Q. 3101262,7.25,,S 418 | 1308,3,"Ware, Mr. Frederick",male,,0,0,359309,8.05,,S 419 | 1309,3,"Peter, Master. Michael J",male,,1,1,2668,22.3583,,C 420 | -------------------------------------------------------------------------------- /easyML/tests/data_files/train.csv: -------------------------------------------------------------------------------- 1 | PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked 2 | 1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S 3 | 2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C 4 | 3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S 5 | 4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S 6 | 5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S 7 | 6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q 8 | 7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S 9 | 8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S 10 | 9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S 11 | 10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C 12 | 11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S 13 | 12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S 14 | 13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S 15 | 14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S 16 | 15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S 17 | 16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S 18 | 17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q 19 | 18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S 20 | 19,0,3,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",female,31,1,0,345763,18,,S 21 | 20,1,3,"Masselmani, Mrs. Fatima",female,,0,0,2649,7.225,,C 22 | 21,0,2,"Fynney, Mr. Joseph J",male,35,0,0,239865,26,,S 23 | 22,1,2,"Beesley, Mr. Lawrence",male,34,0,0,248698,13,D56,S 24 | 23,1,3,"McGowan, Miss. Anna ""Annie""",female,15,0,0,330923,8.0292,,Q 25 | 24,1,1,"Sloper, Mr. William Thompson",male,28,0,0,113788,35.5,A6,S 26 | 25,0,3,"Palsson, Miss. Torborg Danira",female,8,3,1,349909,21.075,,S 27 | 26,1,3,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",female,38,1,5,347077,31.3875,,S 28 | 27,0,3,"Emir, Mr. Farred Chehab",male,,0,0,2631,7.225,,C 29 | 28,0,1,"Fortune, Mr. Charles Alexander",male,19,3,2,19950,263,C23 C25 C27,S 30 | 29,1,3,"O'Dwyer, Miss. Ellen ""Nellie""",female,,0,0,330959,7.8792,,Q 31 | 30,0,3,"Todoroff, Mr. Lalio",male,,0,0,349216,7.8958,,S 32 | 31,0,1,"Uruchurtu, Don. Manuel E",male,40,0,0,PC 17601,27.7208,,C 33 | 32,1,1,"Spencer, Mrs. William Augustus (Marie Eugenie)",female,,1,0,PC 17569,146.5208,B78,C 34 | 33,1,3,"Glynn, Miss. Mary Agatha",female,,0,0,335677,7.75,,Q 35 | 34,0,2,"Wheadon, Mr. Edward H",male,66,0,0,C.A. 24579,10.5,,S 36 | 35,0,1,"Meyer, Mr. Edgar Joseph",male,28,1,0,PC 17604,82.1708,,C 37 | 36,0,1,"Holverson, Mr. Alexander Oskar",male,42,1,0,113789,52,,S 38 | 37,1,3,"Mamee, Mr. Hanna",male,,0,0,2677,7.2292,,C 39 | 38,0,3,"Cann, Mr. Ernest Charles",male,21,0,0,A./5. 2152,8.05,,S 40 | 39,0,3,"Vander Planke, Miss. Augusta Maria",female,18,2,0,345764,18,,S 41 | 40,1,3,"Nicola-Yarred, Miss. Jamila",female,14,1,0,2651,11.2417,,C 42 | 41,0,3,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",female,40,1,0,7546,9.475,,S 43 | 42,0,2,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",female,27,1,0,11668,21,,S 44 | 43,0,3,"Kraeff, Mr. Theodor",male,,0,0,349253,7.8958,,C 45 | 44,1,2,"Laroche, Miss. Simonne Marie Anne Andree",female,3,1,2,SC/Paris 2123,41.5792,,C 46 | 45,1,3,"Devaney, Miss. Margaret Delia",female,19,0,0,330958,7.8792,,Q 47 | 46,0,3,"Rogers, Mr. William John",male,,0,0,S.C./A.4. 23567,8.05,,S 48 | 47,0,3,"Lennon, Mr. Denis",male,,1,0,370371,15.5,,Q 49 | 48,1,3,"O'Driscoll, Miss. Bridget",female,,0,0,14311,7.75,,Q 50 | 49,0,3,"Samaan, Mr. Youssef",male,,2,0,2662,21.6792,,C 51 | 50,0,3,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",female,18,1,0,349237,17.8,,S 52 | 51,0,3,"Panula, Master. Juha Niilo",male,7,4,1,3101295,39.6875,,S 53 | 52,0,3,"Nosworthy, Mr. Richard Cater",male,21,0,0,A/4. 39886,7.8,,S 54 | 53,1,1,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",female,49,1,0,PC 17572,76.7292,D33,C 55 | 54,1,2,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",female,29,1,0,2926,26,,S 56 | 55,0,1,"Ostby, Mr. Engelhart Cornelius",male,65,0,1,113509,61.9792,B30,C 57 | 56,1,1,"Woolner, Mr. Hugh",male,,0,0,19947,35.5,C52,S 58 | 57,1,2,"Rugg, Miss. Emily",female,21,0,0,C.A. 31026,10.5,,S 59 | 58,0,3,"Novel, Mr. Mansouer",male,28.5,0,0,2697,7.2292,,C 60 | 59,1,2,"West, Miss. Constance Mirium",female,5,1,2,C.A. 34651,27.75,,S 61 | 60,0,3,"Goodwin, Master. William Frederick",male,11,5,2,CA 2144,46.9,,S 62 | 61,0,3,"Sirayanian, Mr. Orsen",male,22,0,0,2669,7.2292,,C 63 | 62,1,1,"Icard, Miss. Amelie",female,38,0,0,113572,80,B28, 64 | 63,0,1,"Harris, Mr. Henry Birkhardt",male,45,1,0,36973,83.475,C83,S 65 | 64,0,3,"Skoog, Master. Harald",male,4,3,2,347088,27.9,,S 66 | 65,0,1,"Stewart, Mr. Albert A",male,,0,0,PC 17605,27.7208,,C 67 | 66,1,3,"Moubarek, Master. Gerios",male,,1,1,2661,15.2458,,C 68 | 67,1,2,"Nye, Mrs. (Elizabeth Ramell)",female,29,0,0,C.A. 29395,10.5,F33,S 69 | 68,0,3,"Crease, Mr. Ernest James",male,19,0,0,S.P. 3464,8.1583,,S 70 | 69,1,3,"Andersson, Miss. Erna Alexandra",female,17,4,2,3101281,7.925,,S 71 | 70,0,3,"Kink, Mr. Vincenz",male,26,2,0,315151,8.6625,,S 72 | 71,0,2,"Jenkin, Mr. Stephen Curnow",male,32,0,0,C.A. 33111,10.5,,S 73 | 72,0,3,"Goodwin, Miss. Lillian Amy",female,16,5,2,CA 2144,46.9,,S 74 | 73,0,2,"Hood, Mr. Ambrose Jr",male,21,0,0,S.O.C. 14879,73.5,,S 75 | 74,0,3,"Chronopoulos, Mr. Apostolos",male,26,1,0,2680,14.4542,,C 76 | 75,1,3,"Bing, Mr. Lee",male,32,0,0,1601,56.4958,,S 77 | 76,0,3,"Moen, Mr. Sigurd Hansen",male,25,0,0,348123,7.65,F G73,S 78 | 77,0,3,"Staneff, Mr. Ivan",male,,0,0,349208,7.8958,,S 79 | 78,0,3,"Moutal, Mr. Rahamin Haim",male,,0,0,374746,8.05,,S 80 | 79,1,2,"Caldwell, Master. Alden Gates",male,0.83,0,2,248738,29,,S 81 | 80,1,3,"Dowdell, Miss. Elizabeth",female,30,0,0,364516,12.475,,S 82 | 81,0,3,"Waelens, Mr. Achille",male,22,0,0,345767,9,,S 83 | 82,1,3,"Sheerlinck, Mr. Jan Baptist",male,29,0,0,345779,9.5,,S 84 | 83,1,3,"McDermott, Miss. Brigdet Delia",female,,0,0,330932,7.7875,,Q 85 | 84,0,1,"Carrau, Mr. Francisco M",male,28,0,0,113059,47.1,,S 86 | 85,1,2,"Ilett, Miss. Bertha",female,17,0,0,SO/C 14885,10.5,,S 87 | 86,1,3,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",female,33,3,0,3101278,15.85,,S 88 | 87,0,3,"Ford, Mr. William Neal",male,16,1,3,W./C. 6608,34.375,,S 89 | 88,0,3,"Slocovski, Mr. Selman Francis",male,,0,0,SOTON/OQ 392086,8.05,,S 90 | 89,1,1,"Fortune, Miss. Mabel Helen",female,23,3,2,19950,263,C23 C25 C27,S 91 | 90,0,3,"Celotti, Mr. Francesco",male,24,0,0,343275,8.05,,S 92 | 91,0,3,"Christmann, Mr. Emil",male,29,0,0,343276,8.05,,S 93 | 92,0,3,"Andreasson, Mr. Paul Edvin",male,20,0,0,347466,7.8542,,S 94 | 93,0,1,"Chaffee, Mr. Herbert Fuller",male,46,1,0,W.E.P. 5734,61.175,E31,S 95 | 94,0,3,"Dean, Mr. Bertram Frank",male,26,1,2,C.A. 2315,20.575,,S 96 | 95,0,3,"Coxon, Mr. Daniel",male,59,0,0,364500,7.25,,S 97 | 96,0,3,"Shorney, Mr. Charles Joseph",male,,0,0,374910,8.05,,S 98 | 97,0,1,"Goldschmidt, Mr. George B",male,71,0,0,PC 17754,34.6542,A5,C 99 | 98,1,1,"Greenfield, Mr. William Bertram",male,23,0,1,PC 17759,63.3583,D10 D12,C 100 | 99,1,2,"Doling, Mrs. John T (Ada Julia Bone)",female,34,0,1,231919,23,,S 101 | 100,0,2,"Kantor, Mr. Sinai",male,34,1,0,244367,26,,S 102 | 101,0,3,"Petranec, Miss. Matilda",female,28,0,0,349245,7.8958,,S 103 | 102,0,3,"Petroff, Mr. Pastcho (""Pentcho"")",male,,0,0,349215,7.8958,,S 104 | 103,0,1,"White, Mr. Richard Frasar",male,21,0,1,35281,77.2875,D26,S 105 | 104,0,3,"Johansson, Mr. Gustaf Joel",male,33,0,0,7540,8.6542,,S 106 | 105,0,3,"Gustafsson, Mr. Anders Vilhelm",male,37,2,0,3101276,7.925,,S 107 | 106,0,3,"Mionoff, Mr. Stoytcho",male,28,0,0,349207,7.8958,,S 108 | 107,1,3,"Salkjelsvik, Miss. Anna Kristine",female,21,0,0,343120,7.65,,S 109 | 108,1,3,"Moss, Mr. Albert Johan",male,,0,0,312991,7.775,,S 110 | 109,0,3,"Rekic, Mr. Tido",male,38,0,0,349249,7.8958,,S 111 | 110,1,3,"Moran, Miss. Bertha",female,,1,0,371110,24.15,,Q 112 | 111,0,1,"Porter, Mr. Walter Chamberlain",male,47,0,0,110465,52,C110,S 113 | 112,0,3,"Zabour, Miss. Hileni",female,14.5,1,0,2665,14.4542,,C 114 | 113,0,3,"Barton, Mr. David John",male,22,0,0,324669,8.05,,S 115 | 114,0,3,"Jussila, Miss. Katriina",female,20,1,0,4136,9.825,,S 116 | 115,0,3,"Attalah, Miss. Malake",female,17,0,0,2627,14.4583,,C 117 | 116,0,3,"Pekoniemi, Mr. Edvard",male,21,0,0,STON/O 2. 3101294,7.925,,S 118 | 117,0,3,"Connors, Mr. Patrick",male,70.5,0,0,370369,7.75,,Q 119 | 118,0,2,"Turpin, Mr. William John Robert",male,29,1,0,11668,21,,S 120 | 119,0,1,"Baxter, Mr. Quigg Edmond",male,24,0,1,PC 17558,247.5208,B58 B60,C 121 | 120,0,3,"Andersson, Miss. Ellis Anna Maria",female,2,4,2,347082,31.275,,S 122 | 121,0,2,"Hickman, Mr. Stanley George",male,21,2,0,S.O.C. 14879,73.5,,S 123 | 122,0,3,"Moore, Mr. Leonard Charles",male,,0,0,A4. 54510,8.05,,S 124 | 123,0,2,"Nasser, Mr. Nicholas",male,32.5,1,0,237736,30.0708,,C 125 | 124,1,2,"Webber, Miss. Susan",female,32.5,0,0,27267,13,E101,S 126 | 125,0,1,"White, Mr. Percival Wayland",male,54,0,1,35281,77.2875,D26,S 127 | 126,1,3,"Nicola-Yarred, Master. Elias",male,12,1,0,2651,11.2417,,C 128 | 127,0,3,"McMahon, Mr. Martin",male,,0,0,370372,7.75,,Q 129 | 128,1,3,"Madsen, Mr. Fridtjof Arne",male,24,0,0,C 17369,7.1417,,S 130 | 129,1,3,"Peter, Miss. Anna",female,,1,1,2668,22.3583,F E69,C 131 | 130,0,3,"Ekstrom, Mr. Johan",male,45,0,0,347061,6.975,,S 132 | 131,0,3,"Drazenoic, Mr. Jozef",male,33,0,0,349241,7.8958,,C 133 | 132,0,3,"Coelho, Mr. Domingos Fernandeo",male,20,0,0,SOTON/O.Q. 3101307,7.05,,S 134 | 133,0,3,"Robins, Mrs. Alexander A (Grace Charity Laury)",female,47,1,0,A/5. 3337,14.5,,S 135 | 134,1,2,"Weisz, Mrs. Leopold (Mathilde Francoise Pede)",female,29,1,0,228414,26,,S 136 | 135,0,2,"Sobey, Mr. Samuel James Hayden",male,25,0,0,C.A. 29178,13,,S 137 | 136,0,2,"Richard, Mr. Emile",male,23,0,0,SC/PARIS 2133,15.0458,,C 138 | 137,1,1,"Newsom, Miss. Helen Monypeny",female,19,0,2,11752,26.2833,D47,S 139 | 138,0,1,"Futrelle, Mr. Jacques Heath",male,37,1,0,113803,53.1,C123,S 140 | 139,0,3,"Osen, Mr. Olaf Elon",male,16,0,0,7534,9.2167,,S 141 | 140,0,1,"Giglio, Mr. Victor",male,24,0,0,PC 17593,79.2,B86,C 142 | 141,0,3,"Boulos, Mrs. Joseph (Sultana)",female,,0,2,2678,15.2458,,C 143 | 142,1,3,"Nysten, Miss. Anna Sofia",female,22,0,0,347081,7.75,,S 144 | 143,1,3,"Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck)",female,24,1,0,STON/O2. 3101279,15.85,,S 145 | 144,0,3,"Burke, Mr. Jeremiah",male,19,0,0,365222,6.75,,Q 146 | 145,0,2,"Andrew, Mr. Edgardo Samuel",male,18,0,0,231945,11.5,,S 147 | 146,0,2,"Nicholls, Mr. Joseph Charles",male,19,1,1,C.A. 33112,36.75,,S 148 | 147,1,3,"Andersson, Mr. August Edvard (""Wennerstrom"")",male,27,0,0,350043,7.7958,,S 149 | 148,0,3,"Ford, Miss. Robina Maggie ""Ruby""",female,9,2,2,W./C. 6608,34.375,,S 150 | 149,0,2,"Navratil, Mr. Michel (""Louis M Hoffman"")",male,36.5,0,2,230080,26,F2,S 151 | 150,0,2,"Byles, Rev. Thomas Roussel Davids",male,42,0,0,244310,13,,S 152 | 151,0,2,"Bateman, Rev. Robert James",male,51,0,0,S.O.P. 1166,12.525,,S 153 | 152,1,1,"Pears, Mrs. Thomas (Edith Wearne)",female,22,1,0,113776,66.6,C2,S 154 | 153,0,3,"Meo, Mr. Alfonzo",male,55.5,0,0,A.5. 11206,8.05,,S 155 | 154,0,3,"van Billiard, Mr. Austin Blyler",male,40.5,0,2,A/5. 851,14.5,,S 156 | 155,0,3,"Olsen, Mr. Ole Martin",male,,0,0,Fa 265302,7.3125,,S 157 | 156,0,1,"Williams, Mr. Charles Duane",male,51,0,1,PC 17597,61.3792,,C 158 | 157,1,3,"Gilnagh, Miss. Katherine ""Katie""",female,16,0,0,35851,7.7333,,Q 159 | 158,0,3,"Corn, Mr. Harry",male,30,0,0,SOTON/OQ 392090,8.05,,S 160 | 159,0,3,"Smiljanic, Mr. Mile",male,,0,0,315037,8.6625,,S 161 | 160,0,3,"Sage, Master. Thomas Henry",male,,8,2,CA. 2343,69.55,,S 162 | 161,0,3,"Cribb, Mr. John Hatfield",male,44,0,1,371362,16.1,,S 163 | 162,1,2,"Watt, Mrs. James (Elizabeth ""Bessie"" Inglis Milne)",female,40,0,0,C.A. 33595,15.75,,S 164 | 163,0,3,"Bengtsson, Mr. John Viktor",male,26,0,0,347068,7.775,,S 165 | 164,0,3,"Calic, Mr. Jovo",male,17,0,0,315093,8.6625,,S 166 | 165,0,3,"Panula, Master. Eino Viljami",male,1,4,1,3101295,39.6875,,S 167 | 166,1,3,"Goldsmith, Master. Frank John William ""Frankie""",male,9,0,2,363291,20.525,,S 168 | 167,1,1,"Chibnall, Mrs. (Edith Martha Bowerman)",female,,0,1,113505,55,E33,S 169 | 168,0,3,"Skoog, Mrs. William (Anna Bernhardina Karlsson)",female,45,1,4,347088,27.9,,S 170 | 169,0,1,"Baumann, Mr. John D",male,,0,0,PC 17318,25.925,,S 171 | 170,0,3,"Ling, Mr. Lee",male,28,0,0,1601,56.4958,,S 172 | 171,0,1,"Van der hoef, Mr. Wyckoff",male,61,0,0,111240,33.5,B19,S 173 | 172,0,3,"Rice, Master. Arthur",male,4,4,1,382652,29.125,,Q 174 | 173,1,3,"Johnson, Miss. Eleanor Ileen",female,1,1,1,347742,11.1333,,S 175 | 174,0,3,"Sivola, Mr. Antti Wilhelm",male,21,0,0,STON/O 2. 3101280,7.925,,S 176 | 175,0,1,"Smith, Mr. James Clinch",male,56,0,0,17764,30.6958,A7,C 177 | 176,0,3,"Klasen, Mr. Klas Albin",male,18,1,1,350404,7.8542,,S 178 | 177,0,3,"Lefebre, Master. Henry Forbes",male,,3,1,4133,25.4667,,S 179 | 178,0,1,"Isham, Miss. Ann Elizabeth",female,50,0,0,PC 17595,28.7125,C49,C 180 | 179,0,2,"Hale, Mr. Reginald",male,30,0,0,250653,13,,S 181 | 180,0,3,"Leonard, Mr. Lionel",male,36,0,0,LINE,0,,S 182 | 181,0,3,"Sage, Miss. Constance Gladys",female,,8,2,CA. 2343,69.55,,S 183 | 182,0,2,"Pernot, Mr. Rene",male,,0,0,SC/PARIS 2131,15.05,,C 184 | 183,0,3,"Asplund, Master. Clarence Gustaf Hugo",male,9,4,2,347077,31.3875,,S 185 | 184,1,2,"Becker, Master. Richard F",male,1,2,1,230136,39,F4,S 186 | 185,1,3,"Kink-Heilmann, Miss. Luise Gretchen",female,4,0,2,315153,22.025,,S 187 | 186,0,1,"Rood, Mr. Hugh Roscoe",male,,0,0,113767,50,A32,S 188 | 187,1,3,"O'Brien, Mrs. Thomas (Johanna ""Hannah"" Godfrey)",female,,1,0,370365,15.5,,Q 189 | 188,1,1,"Romaine, Mr. Charles Hallace (""Mr C Rolmane"")",male,45,0,0,111428,26.55,,S 190 | 189,0,3,"Bourke, Mr. John",male,40,1,1,364849,15.5,,Q 191 | 190,0,3,"Turcin, Mr. Stjepan",male,36,0,0,349247,7.8958,,S 192 | 191,1,2,"Pinsky, Mrs. (Rosa)",female,32,0,0,234604,13,,S 193 | 192,0,2,"Carbines, Mr. William",male,19,0,0,28424,13,,S 194 | 193,1,3,"Andersen-Jensen, Miss. Carla Christine Nielsine",female,19,1,0,350046,7.8542,,S 195 | 194,1,2,"Navratil, Master. Michel M",male,3,1,1,230080,26,F2,S 196 | 195,1,1,"Brown, Mrs. James Joseph (Margaret Tobin)",female,44,0,0,PC 17610,27.7208,B4,C 197 | 196,1,1,"Lurette, Miss. Elise",female,58,0,0,PC 17569,146.5208,B80,C 198 | 197,0,3,"Mernagh, Mr. Robert",male,,0,0,368703,7.75,,Q 199 | 198,0,3,"Olsen, Mr. Karl Siegwart Andreas",male,42,0,1,4579,8.4042,,S 200 | 199,1,3,"Madigan, Miss. Margaret ""Maggie""",female,,0,0,370370,7.75,,Q 201 | 200,0,2,"Yrois, Miss. Henriette (""Mrs Harbeck"")",female,24,0,0,248747,13,,S 202 | 201,0,3,"Vande Walle, Mr. Nestor Cyriel",male,28,0,0,345770,9.5,,S 203 | 202,0,3,"Sage, Mr. Frederick",male,,8,2,CA. 2343,69.55,,S 204 | 203,0,3,"Johanson, Mr. Jakob Alfred",male,34,0,0,3101264,6.4958,,S 205 | 204,0,3,"Youseff, Mr. Gerious",male,45.5,0,0,2628,7.225,,C 206 | 205,1,3,"Cohen, Mr. Gurshon ""Gus""",male,18,0,0,A/5 3540,8.05,,S 207 | 206,0,3,"Strom, Miss. Telma Matilda",female,2,0,1,347054,10.4625,G6,S 208 | 207,0,3,"Backstrom, Mr. Karl Alfred",male,32,1,0,3101278,15.85,,S 209 | 208,1,3,"Albimona, Mr. Nassef Cassem",male,26,0,0,2699,18.7875,,C 210 | 209,1,3,"Carr, Miss. Helen ""Ellen""",female,16,0,0,367231,7.75,,Q 211 | 210,1,1,"Blank, Mr. Henry",male,40,0,0,112277,31,A31,C 212 | 211,0,3,"Ali, Mr. Ahmed",male,24,0,0,SOTON/O.Q. 3101311,7.05,,S 213 | 212,1,2,"Cameron, Miss. Clear Annie",female,35,0,0,F.C.C. 13528,21,,S 214 | 213,0,3,"Perkin, Mr. John Henry",male,22,0,0,A/5 21174,7.25,,S 215 | 214,0,2,"Givard, Mr. Hans Kristensen",male,30,0,0,250646,13,,S 216 | 215,0,3,"Kiernan, Mr. Philip",male,,1,0,367229,7.75,,Q 217 | 216,1,1,"Newell, Miss. Madeleine",female,31,1,0,35273,113.275,D36,C 218 | 217,1,3,"Honkanen, Miss. Eliina",female,27,0,0,STON/O2. 3101283,7.925,,S 219 | 218,0,2,"Jacobsohn, Mr. Sidney Samuel",male,42,1,0,243847,27,,S 220 | 219,1,1,"Bazzani, Miss. Albina",female,32,0,0,11813,76.2917,D15,C 221 | 220,0,2,"Harris, Mr. Walter",male,30,0,0,W/C 14208,10.5,,S 222 | 221,1,3,"Sunderland, Mr. Victor Francis",male,16,0,0,SOTON/OQ 392089,8.05,,S 223 | 222,0,2,"Bracken, Mr. James H",male,27,0,0,220367,13,,S 224 | 223,0,3,"Green, Mr. George Henry",male,51,0,0,21440,8.05,,S 225 | 224,0,3,"Nenkoff, Mr. Christo",male,,0,0,349234,7.8958,,S 226 | 225,1,1,"Hoyt, Mr. Frederick Maxfield",male,38,1,0,19943,90,C93,S 227 | 226,0,3,"Berglund, Mr. Karl Ivar Sven",male,22,0,0,PP 4348,9.35,,S 228 | 227,1,2,"Mellors, Mr. William John",male,19,0,0,SW/PP 751,10.5,,S 229 | 228,0,3,"Lovell, Mr. John Hall (""Henry"")",male,20.5,0,0,A/5 21173,7.25,,S 230 | 229,0,2,"Fahlstrom, Mr. Arne Jonas",male,18,0,0,236171,13,,S 231 | 230,0,3,"Lefebre, Miss. Mathilde",female,,3,1,4133,25.4667,,S 232 | 231,1,1,"Harris, Mrs. Henry Birkhardt (Irene Wallach)",female,35,1,0,36973,83.475,C83,S 233 | 232,0,3,"Larsson, Mr. Bengt Edvin",male,29,0,0,347067,7.775,,S 234 | 233,0,2,"Sjostedt, Mr. Ernst Adolf",male,59,0,0,237442,13.5,,S 235 | 234,1,3,"Asplund, Miss. Lillian Gertrud",female,5,4,2,347077,31.3875,,S 236 | 235,0,2,"Leyson, Mr. Robert William Norman",male,24,0,0,C.A. 29566,10.5,,S 237 | 236,0,3,"Harknett, Miss. Alice Phoebe",female,,0,0,W./C. 6609,7.55,,S 238 | 237,0,2,"Hold, Mr. Stephen",male,44,1,0,26707,26,,S 239 | 238,1,2,"Collyer, Miss. Marjorie ""Lottie""",female,8,0,2,C.A. 31921,26.25,,S 240 | 239,0,2,"Pengelly, Mr. Frederick William",male,19,0,0,28665,10.5,,S 241 | 240,0,2,"Hunt, Mr. George Henry",male,33,0,0,SCO/W 1585,12.275,,S 242 | 241,0,3,"Zabour, Miss. Thamine",female,,1,0,2665,14.4542,,C 243 | 242,1,3,"Murphy, Miss. Katherine ""Kate""",female,,1,0,367230,15.5,,Q 244 | 243,0,2,"Coleridge, Mr. Reginald Charles",male,29,0,0,W./C. 14263,10.5,,S 245 | 244,0,3,"Maenpaa, Mr. Matti Alexanteri",male,22,0,0,STON/O 2. 3101275,7.125,,S 246 | 245,0,3,"Attalah, Mr. Sleiman",male,30,0,0,2694,7.225,,C 247 | 246,0,1,"Minahan, Dr. William Edward",male,44,2,0,19928,90,C78,Q 248 | 247,0,3,"Lindahl, Miss. Agda Thorilda Viktoria",female,25,0,0,347071,7.775,,S 249 | 248,1,2,"Hamalainen, Mrs. William (Anna)",female,24,0,2,250649,14.5,,S 250 | 249,1,1,"Beckwith, Mr. Richard Leonard",male,37,1,1,11751,52.5542,D35,S 251 | 250,0,2,"Carter, Rev. Ernest Courtenay",male,54,1,0,244252,26,,S 252 | 251,0,3,"Reed, Mr. James George",male,,0,0,362316,7.25,,S 253 | 252,0,3,"Strom, Mrs. Wilhelm (Elna Matilda Persson)",female,29,1,1,347054,10.4625,G6,S 254 | 253,0,1,"Stead, Mr. William Thomas",male,62,0,0,113514,26.55,C87,S 255 | 254,0,3,"Lobb, Mr. William Arthur",male,30,1,0,A/5. 3336,16.1,,S 256 | 255,0,3,"Rosblom, Mrs. Viktor (Helena Wilhelmina)",female,41,0,2,370129,20.2125,,S 257 | 256,1,3,"Touma, Mrs. Darwis (Hanne Youssef Razi)",female,29,0,2,2650,15.2458,,C 258 | 257,1,1,"Thorne, Mrs. Gertrude Maybelle",female,,0,0,PC 17585,79.2,,C 259 | 258,1,1,"Cherry, Miss. Gladys",female,30,0,0,110152,86.5,B77,S 260 | 259,1,1,"Ward, Miss. Anna",female,35,0,0,PC 17755,512.3292,,C 261 | 260,1,2,"Parrish, Mrs. (Lutie Davis)",female,50,0,1,230433,26,,S 262 | 261,0,3,"Smith, Mr. Thomas",male,,0,0,384461,7.75,,Q 263 | 262,1,3,"Asplund, Master. Edvin Rojj Felix",male,3,4,2,347077,31.3875,,S 264 | 263,0,1,"Taussig, Mr. Emil",male,52,1,1,110413,79.65,E67,S 265 | 264,0,1,"Harrison, Mr. William",male,40,0,0,112059,0,B94,S 266 | 265,0,3,"Henry, Miss. Delia",female,,0,0,382649,7.75,,Q 267 | 266,0,2,"Reeves, Mr. David",male,36,0,0,C.A. 17248,10.5,,S 268 | 267,0,3,"Panula, Mr. Ernesti Arvid",male,16,4,1,3101295,39.6875,,S 269 | 268,1,3,"Persson, Mr. Ernst Ulrik",male,25,1,0,347083,7.775,,S 270 | 269,1,1,"Graham, Mrs. William Thompson (Edith Junkins)",female,58,0,1,PC 17582,153.4625,C125,S 271 | 270,1,1,"Bissette, Miss. Amelia",female,35,0,0,PC 17760,135.6333,C99,S 272 | 271,0,1,"Cairns, Mr. Alexander",male,,0,0,113798,31,,S 273 | 272,1,3,"Tornquist, Mr. William Henry",male,25,0,0,LINE,0,,S 274 | 273,1,2,"Mellinger, Mrs. (Elizabeth Anne Maidment)",female,41,0,1,250644,19.5,,S 275 | 274,0,1,"Natsch, Mr. Charles H",male,37,0,1,PC 17596,29.7,C118,C 276 | 275,1,3,"Healy, Miss. Hanora ""Nora""",female,,0,0,370375,7.75,,Q 277 | 276,1,1,"Andrews, Miss. Kornelia Theodosia",female,63,1,0,13502,77.9583,D7,S 278 | 277,0,3,"Lindblom, Miss. Augusta Charlotta",female,45,0,0,347073,7.75,,S 279 | 278,0,2,"Parkes, Mr. Francis ""Frank""",male,,0,0,239853,0,,S 280 | 279,0,3,"Rice, Master. Eric",male,7,4,1,382652,29.125,,Q 281 | 280,1,3,"Abbott, Mrs. Stanton (Rosa Hunt)",female,35,1,1,C.A. 2673,20.25,,S 282 | 281,0,3,"Duane, Mr. Frank",male,65,0,0,336439,7.75,,Q 283 | 282,0,3,"Olsson, Mr. Nils Johan Goransson",male,28,0,0,347464,7.8542,,S 284 | 283,0,3,"de Pelsmaeker, Mr. Alfons",male,16,0,0,345778,9.5,,S 285 | 284,1,3,"Dorking, Mr. Edward Arthur",male,19,0,0,A/5. 10482,8.05,,S 286 | 285,0,1,"Smith, Mr. Richard William",male,,0,0,113056,26,A19,S 287 | 286,0,3,"Stankovic, Mr. Ivan",male,33,0,0,349239,8.6625,,C 288 | 287,1,3,"de Mulder, Mr. Theodore",male,30,0,0,345774,9.5,,S 289 | 288,0,3,"Naidenoff, Mr. Penko",male,22,0,0,349206,7.8958,,S 290 | 289,1,2,"Hosono, Mr. Masabumi",male,42,0,0,237798,13,,S 291 | 290,1,3,"Connolly, Miss. Kate",female,22,0,0,370373,7.75,,Q 292 | 291,1,1,"Barber, Miss. Ellen ""Nellie""",female,26,0,0,19877,78.85,,S 293 | 292,1,1,"Bishop, Mrs. Dickinson H (Helen Walton)",female,19,1,0,11967,91.0792,B49,C 294 | 293,0,2,"Levy, Mr. Rene Jacques",male,36,0,0,SC/Paris 2163,12.875,D,C 295 | 294,0,3,"Haas, Miss. Aloisia",female,24,0,0,349236,8.85,,S 296 | 295,0,3,"Mineff, Mr. Ivan",male,24,0,0,349233,7.8958,,S 297 | 296,0,1,"Lewy, Mr. Ervin G",male,,0,0,PC 17612,27.7208,,C 298 | 297,0,3,"Hanna, Mr. Mansour",male,23.5,0,0,2693,7.2292,,C 299 | 298,0,1,"Allison, Miss. Helen Loraine",female,2,1,2,113781,151.55,C22 C26,S 300 | 299,1,1,"Saalfeld, Mr. Adolphe",male,,0,0,19988,30.5,C106,S 301 | 300,1,1,"Baxter, Mrs. James (Helene DeLaudeniere Chaput)",female,50,0,1,PC 17558,247.5208,B58 B60,C 302 | 301,1,3,"Kelly, Miss. Anna Katherine ""Annie Kate""",female,,0,0,9234,7.75,,Q 303 | 302,1,3,"McCoy, Mr. Bernard",male,,2,0,367226,23.25,,Q 304 | 303,0,3,"Johnson, Mr. William Cahoone Jr",male,19,0,0,LINE,0,,S 305 | 304,1,2,"Keane, Miss. Nora A",female,,0,0,226593,12.35,E101,Q 306 | 305,0,3,"Williams, Mr. Howard Hugh ""Harry""",male,,0,0,A/5 2466,8.05,,S 307 | 306,1,1,"Allison, Master. Hudson Trevor",male,0.92,1,2,113781,151.55,C22 C26,S 308 | 307,1,1,"Fleming, Miss. Margaret",female,,0,0,17421,110.8833,,C 309 | 308,1,1,"Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)",female,17,1,0,PC 17758,108.9,C65,C 310 | 309,0,2,"Abelson, Mr. Samuel",male,30,1,0,P/PP 3381,24,,C 311 | 310,1,1,"Francatelli, Miss. Laura Mabel",female,30,0,0,PC 17485,56.9292,E36,C 312 | 311,1,1,"Hays, Miss. Margaret Bechstein",female,24,0,0,11767,83.1583,C54,C 313 | 312,1,1,"Ryerson, Miss. Emily Borie",female,18,2,2,PC 17608,262.375,B57 B59 B63 B66,C 314 | 313,0,2,"Lahtinen, Mrs. William (Anna Sylfven)",female,26,1,1,250651,26,,S 315 | 314,0,3,"Hendekovic, Mr. Ignjac",male,28,0,0,349243,7.8958,,S 316 | 315,0,2,"Hart, Mr. Benjamin",male,43,1,1,F.C.C. 13529,26.25,,S 317 | 316,1,3,"Nilsson, Miss. Helmina Josefina",female,26,0,0,347470,7.8542,,S 318 | 317,1,2,"Kantor, Mrs. Sinai (Miriam Sternin)",female,24,1,0,244367,26,,S 319 | 318,0,2,"Moraweck, Dr. Ernest",male,54,0,0,29011,14,,S 320 | 319,1,1,"Wick, Miss. Mary Natalie",female,31,0,2,36928,164.8667,C7,S 321 | 320,1,1,"Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone)",female,40,1,1,16966,134.5,E34,C 322 | 321,0,3,"Dennis, Mr. Samuel",male,22,0,0,A/5 21172,7.25,,S 323 | 322,0,3,"Danoff, Mr. Yoto",male,27,0,0,349219,7.8958,,S 324 | 323,1,2,"Slayter, Miss. Hilda Mary",female,30,0,0,234818,12.35,,Q 325 | 324,1,2,"Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh)",female,22,1,1,248738,29,,S 326 | 325,0,3,"Sage, Mr. George John Jr",male,,8,2,CA. 2343,69.55,,S 327 | 326,1,1,"Young, Miss. Marie Grice",female,36,0,0,PC 17760,135.6333,C32,C 328 | 327,0,3,"Nysveen, Mr. Johan Hansen",male,61,0,0,345364,6.2375,,S 329 | 328,1,2,"Ball, Mrs. (Ada E Hall)",female,36,0,0,28551,13,D,S 330 | 329,1,3,"Goldsmith, Mrs. Frank John (Emily Alice Brown)",female,31,1,1,363291,20.525,,S 331 | 330,1,1,"Hippach, Miss. Jean Gertrude",female,16,0,1,111361,57.9792,B18,C 332 | 331,1,3,"McCoy, Miss. Agnes",female,,2,0,367226,23.25,,Q 333 | 332,0,1,"Partner, Mr. Austen",male,45.5,0,0,113043,28.5,C124,S 334 | 333,0,1,"Graham, Mr. George Edward",male,38,0,1,PC 17582,153.4625,C91,S 335 | 334,0,3,"Vander Planke, Mr. Leo Edmondus",male,16,2,0,345764,18,,S 336 | 335,1,1,"Frauenthal, Mrs. Henry William (Clara Heinsheimer)",female,,1,0,PC 17611,133.65,,S 337 | 336,0,3,"Denkoff, Mr. Mitto",male,,0,0,349225,7.8958,,S 338 | 337,0,1,"Pears, Mr. Thomas Clinton",male,29,1,0,113776,66.6,C2,S 339 | 338,1,1,"Burns, Miss. Elizabeth Margaret",female,41,0,0,16966,134.5,E40,C 340 | 339,1,3,"Dahl, Mr. Karl Edwart",male,45,0,0,7598,8.05,,S 341 | 340,0,1,"Blackwell, Mr. Stephen Weart",male,45,0,0,113784,35.5,T,S 342 | 341,1,2,"Navratil, Master. Edmond Roger",male,2,1,1,230080,26,F2,S 343 | 342,1,1,"Fortune, Miss. Alice Elizabeth",female,24,3,2,19950,263,C23 C25 C27,S 344 | 343,0,2,"Collander, Mr. Erik Gustaf",male,28,0,0,248740,13,,S 345 | 344,0,2,"Sedgwick, Mr. Charles Frederick Waddington",male,25,0,0,244361,13,,S 346 | 345,0,2,"Fox, Mr. Stanley Hubert",male,36,0,0,229236,13,,S 347 | 346,1,2,"Brown, Miss. Amelia ""Mildred""",female,24,0,0,248733,13,F33,S 348 | 347,1,2,"Smith, Miss. Marion Elsie",female,40,0,0,31418,13,,S 349 | 348,1,3,"Davison, Mrs. Thomas Henry (Mary E Finck)",female,,1,0,386525,16.1,,S 350 | 349,1,3,"Coutts, Master. William Loch ""William""",male,3,1,1,C.A. 37671,15.9,,S 351 | 350,0,3,"Dimic, Mr. Jovan",male,42,0,0,315088,8.6625,,S 352 | 351,0,3,"Odahl, Mr. Nils Martin",male,23,0,0,7267,9.225,,S 353 | 352,0,1,"Williams-Lambert, Mr. Fletcher Fellows",male,,0,0,113510,35,C128,S 354 | 353,0,3,"Elias, Mr. Tannous",male,15,1,1,2695,7.2292,,C 355 | 354,0,3,"Arnold-Franchi, Mr. Josef",male,25,1,0,349237,17.8,,S 356 | 355,0,3,"Yousif, Mr. Wazli",male,,0,0,2647,7.225,,C 357 | 356,0,3,"Vanden Steen, Mr. Leo Peter",male,28,0,0,345783,9.5,,S 358 | 357,1,1,"Bowerman, Miss. Elsie Edith",female,22,0,1,113505,55,E33,S 359 | 358,0,2,"Funk, Miss. Annie Clemmer",female,38,0,0,237671,13,,S 360 | 359,1,3,"McGovern, Miss. Mary",female,,0,0,330931,7.8792,,Q 361 | 360,1,3,"Mockler, Miss. Helen Mary ""Ellie""",female,,0,0,330980,7.8792,,Q 362 | 361,0,3,"Skoog, Mr. Wilhelm",male,40,1,4,347088,27.9,,S 363 | 362,0,2,"del Carlo, Mr. Sebastiano",male,29,1,0,SC/PARIS 2167,27.7208,,C 364 | 363,0,3,"Barbara, Mrs. (Catherine David)",female,45,0,1,2691,14.4542,,C 365 | 364,0,3,"Asim, Mr. Adola",male,35,0,0,SOTON/O.Q. 3101310,7.05,,S 366 | 365,0,3,"O'Brien, Mr. Thomas",male,,1,0,370365,15.5,,Q 367 | 366,0,3,"Adahl, Mr. Mauritz Nils Martin",male,30,0,0,C 7076,7.25,,S 368 | 367,1,1,"Warren, Mrs. Frank Manley (Anna Sophia Atkinson)",female,60,1,0,110813,75.25,D37,C 369 | 368,1,3,"Moussa, Mrs. (Mantoura Boulos)",female,,0,0,2626,7.2292,,C 370 | 369,1,3,"Jermyn, Miss. Annie",female,,0,0,14313,7.75,,Q 371 | 370,1,1,"Aubart, Mme. Leontine Pauline",female,24,0,0,PC 17477,69.3,B35,C 372 | 371,1,1,"Harder, Mr. George Achilles",male,25,1,0,11765,55.4417,E50,C 373 | 372,0,3,"Wiklund, Mr. Jakob Alfred",male,18,1,0,3101267,6.4958,,S 374 | 373,0,3,"Beavan, Mr. William Thomas",male,19,0,0,323951,8.05,,S 375 | 374,0,1,"Ringhini, Mr. Sante",male,22,0,0,PC 17760,135.6333,,C 376 | 375,0,3,"Palsson, Miss. Stina Viola",female,3,3,1,349909,21.075,,S 377 | 376,1,1,"Meyer, Mrs. Edgar Joseph (Leila Saks)",female,,1,0,PC 17604,82.1708,,C 378 | 377,1,3,"Landergren, Miss. Aurora Adelia",female,22,0,0,C 7077,7.25,,S 379 | 378,0,1,"Widener, Mr. Harry Elkins",male,27,0,2,113503,211.5,C82,C 380 | 379,0,3,"Betros, Mr. Tannous",male,20,0,0,2648,4.0125,,C 381 | 380,0,3,"Gustafsson, Mr. Karl Gideon",male,19,0,0,347069,7.775,,S 382 | 381,1,1,"Bidois, Miss. Rosalie",female,42,0,0,PC 17757,227.525,,C 383 | 382,1,3,"Nakid, Miss. Maria (""Mary"")",female,1,0,2,2653,15.7417,,C 384 | 383,0,3,"Tikkanen, Mr. Juho",male,32,0,0,STON/O 2. 3101293,7.925,,S 385 | 384,1,1,"Holverson, Mrs. Alexander Oskar (Mary Aline Towner)",female,35,1,0,113789,52,,S 386 | 385,0,3,"Plotcharsky, Mr. Vasil",male,,0,0,349227,7.8958,,S 387 | 386,0,2,"Davies, Mr. Charles Henry",male,18,0,0,S.O.C. 14879,73.5,,S 388 | 387,0,3,"Goodwin, Master. Sidney Leonard",male,1,5,2,CA 2144,46.9,,S 389 | 388,1,2,"Buss, Miss. Kate",female,36,0,0,27849,13,,S 390 | 389,0,3,"Sadlier, Mr. Matthew",male,,0,0,367655,7.7292,,Q 391 | 390,1,2,"Lehmann, Miss. Bertha",female,17,0,0,SC 1748,12,,C 392 | 391,1,1,"Carter, Mr. William Ernest",male,36,1,2,113760,120,B96 B98,S 393 | 392,1,3,"Jansson, Mr. Carl Olof",male,21,0,0,350034,7.7958,,S 394 | 393,0,3,"Gustafsson, Mr. Johan Birger",male,28,2,0,3101277,7.925,,S 395 | 394,1,1,"Newell, Miss. Marjorie",female,23,1,0,35273,113.275,D36,C 396 | 395,1,3,"Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson)",female,24,0,2,PP 9549,16.7,G6,S 397 | 396,0,3,"Johansson, Mr. Erik",male,22,0,0,350052,7.7958,,S 398 | 397,0,3,"Olsson, Miss. Elina",female,31,0,0,350407,7.8542,,S 399 | 398,0,2,"McKane, Mr. Peter David",male,46,0,0,28403,26,,S 400 | 399,0,2,"Pain, Dr. Alfred",male,23,0,0,244278,10.5,,S 401 | 400,1,2,"Trout, Mrs. William H (Jessie L)",female,28,0,0,240929,12.65,,S 402 | 401,1,3,"Niskanen, Mr. Juha",male,39,0,0,STON/O 2. 3101289,7.925,,S 403 | 402,0,3,"Adams, Mr. John",male,26,0,0,341826,8.05,,S 404 | 403,0,3,"Jussila, Miss. Mari Aina",female,21,1,0,4137,9.825,,S 405 | 404,0,3,"Hakkarainen, Mr. Pekka Pietari",male,28,1,0,STON/O2. 3101279,15.85,,S 406 | 405,0,3,"Oreskovic, Miss. Marija",female,20,0,0,315096,8.6625,,S 407 | 406,0,2,"Gale, Mr. Shadrach",male,34,1,0,28664,21,,S 408 | 407,0,3,"Widegren, Mr. Carl/Charles Peter",male,51,0,0,347064,7.75,,S 409 | 408,1,2,"Richards, Master. William Rowe",male,3,1,1,29106,18.75,,S 410 | 409,0,3,"Birkeland, Mr. Hans Martin Monsen",male,21,0,0,312992,7.775,,S 411 | 410,0,3,"Lefebre, Miss. Ida",female,,3,1,4133,25.4667,,S 412 | 411,0,3,"Sdycoff, Mr. Todor",male,,0,0,349222,7.8958,,S 413 | 412,0,3,"Hart, Mr. Henry",male,,0,0,394140,6.8583,,Q 414 | 413,1,1,"Minahan, Miss. Daisy E",female,33,1,0,19928,90,C78,Q 415 | 414,0,2,"Cunningham, Mr. Alfred Fleming",male,,0,0,239853,0,,S 416 | 415,1,3,"Sundman, Mr. Johan Julian",male,44,0,0,STON/O 2. 3101269,7.925,,S 417 | 416,0,3,"Meek, Mrs. Thomas (Annie Louise Rowley)",female,,0,0,343095,8.05,,S 418 | 417,1,2,"Drew, Mrs. James Vivian (Lulu Thorne Christian)",female,34,1,1,28220,32.5,,S 419 | 418,1,2,"Silven, Miss. Lyyli Karoliina",female,18,0,2,250652,13,,S 420 | 419,0,2,"Matthews, Mr. William John",male,30,0,0,28228,13,,S 421 | 420,0,3,"Van Impe, Miss. Catharina",female,10,0,2,345773,24.15,,S 422 | 421,0,3,"Gheorgheff, Mr. Stanio",male,,0,0,349254,7.8958,,C 423 | 422,0,3,"Charters, Mr. David",male,21,0,0,A/5. 13032,7.7333,,Q 424 | 423,0,3,"Zimmerman, Mr. Leo",male,29,0,0,315082,7.875,,S 425 | 424,0,3,"Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren)",female,28,1,1,347080,14.4,,S 426 | 425,0,3,"Rosblom, Mr. Viktor Richard",male,18,1,1,370129,20.2125,,S 427 | 426,0,3,"Wiseman, Mr. Phillippe",male,,0,0,A/4. 34244,7.25,,S 428 | 427,1,2,"Clarke, Mrs. Charles V (Ada Maria Winfield)",female,28,1,0,2003,26,,S 429 | 428,1,2,"Phillips, Miss. Kate Florence (""Mrs Kate Louise Phillips Marshall"")",female,19,0,0,250655,26,,S 430 | 429,0,3,"Flynn, Mr. James",male,,0,0,364851,7.75,,Q 431 | 430,1,3,"Pickard, Mr. Berk (Berk Trembisky)",male,32,0,0,SOTON/O.Q. 392078,8.05,E10,S 432 | 431,1,1,"Bjornstrom-Steffansson, Mr. Mauritz Hakan",male,28,0,0,110564,26.55,C52,S 433 | 432,1,3,"Thorneycroft, Mrs. Percival (Florence Kate White)",female,,1,0,376564,16.1,,S 434 | 433,1,2,"Louch, Mrs. Charles Alexander (Alice Adelaide Slow)",female,42,1,0,SC/AH 3085,26,,S 435 | 434,0,3,"Kallio, Mr. Nikolai Erland",male,17,0,0,STON/O 2. 3101274,7.125,,S 436 | 435,0,1,"Silvey, Mr. William Baird",male,50,1,0,13507,55.9,E44,S 437 | 436,1,1,"Carter, Miss. Lucile Polk",female,14,1,2,113760,120,B96 B98,S 438 | 437,0,3,"Ford, Miss. Doolina Margaret ""Daisy""",female,21,2,2,W./C. 6608,34.375,,S 439 | 438,1,2,"Richards, Mrs. Sidney (Emily Hocking)",female,24,2,3,29106,18.75,,S 440 | 439,0,1,"Fortune, Mr. Mark",male,64,1,4,19950,263,C23 C25 C27,S 441 | 440,0,2,"Kvillner, Mr. Johan Henrik Johannesson",male,31,0,0,C.A. 18723,10.5,,S 442 | 441,1,2,"Hart, Mrs. Benjamin (Esther Ada Bloomfield)",female,45,1,1,F.C.C. 13529,26.25,,S 443 | 442,0,3,"Hampe, Mr. Leon",male,20,0,0,345769,9.5,,S 444 | 443,0,3,"Petterson, Mr. Johan Emil",male,25,1,0,347076,7.775,,S 445 | 444,1,2,"Reynaldo, Ms. Encarnacion",female,28,0,0,230434,13,,S 446 | 445,1,3,"Johannesen-Bratthammer, Mr. Bernt",male,,0,0,65306,8.1125,,S 447 | 446,1,1,"Dodge, Master. Washington",male,4,0,2,33638,81.8583,A34,S 448 | 447,1,2,"Mellinger, Miss. Madeleine Violet",female,13,0,1,250644,19.5,,S 449 | 448,1,1,"Seward, Mr. Frederic Kimber",male,34,0,0,113794,26.55,,S 450 | 449,1,3,"Baclini, Miss. Marie Catherine",female,5,2,1,2666,19.2583,,C 451 | 450,1,1,"Peuchen, Major. Arthur Godfrey",male,52,0,0,113786,30.5,C104,S 452 | 451,0,2,"West, Mr. Edwy Arthur",male,36,1,2,C.A. 34651,27.75,,S 453 | 452,0,3,"Hagland, Mr. Ingvald Olai Olsen",male,,1,0,65303,19.9667,,S 454 | 453,0,1,"Foreman, Mr. Benjamin Laventall",male,30,0,0,113051,27.75,C111,C 455 | 454,1,1,"Goldenberg, Mr. Samuel L",male,49,1,0,17453,89.1042,C92,C 456 | 455,0,3,"Peduzzi, Mr. Joseph",male,,0,0,A/5 2817,8.05,,S 457 | 456,1,3,"Jalsevac, Mr. Ivan",male,29,0,0,349240,7.8958,,C 458 | 457,0,1,"Millet, Mr. Francis Davis",male,65,0,0,13509,26.55,E38,S 459 | 458,1,1,"Kenyon, Mrs. Frederick R (Marion)",female,,1,0,17464,51.8625,D21,S 460 | 459,1,2,"Toomey, Miss. Ellen",female,50,0,0,F.C.C. 13531,10.5,,S 461 | 460,0,3,"O'Connor, Mr. Maurice",male,,0,0,371060,7.75,,Q 462 | 461,1,1,"Anderson, Mr. Harry",male,48,0,0,19952,26.55,E12,S 463 | 462,0,3,"Morley, Mr. William",male,34,0,0,364506,8.05,,S 464 | 463,0,1,"Gee, Mr. Arthur H",male,47,0,0,111320,38.5,E63,S 465 | 464,0,2,"Milling, Mr. Jacob Christian",male,48,0,0,234360,13,,S 466 | 465,0,3,"Maisner, Mr. Simon",male,,0,0,A/S 2816,8.05,,S 467 | 466,0,3,"Goncalves, Mr. Manuel Estanslas",male,38,0,0,SOTON/O.Q. 3101306,7.05,,S 468 | 467,0,2,"Campbell, Mr. William",male,,0,0,239853,0,,S 469 | 468,0,1,"Smart, Mr. John Montgomery",male,56,0,0,113792,26.55,,S 470 | 469,0,3,"Scanlan, Mr. James",male,,0,0,36209,7.725,,Q 471 | 470,1,3,"Baclini, Miss. Helene Barbara",female,0.75,2,1,2666,19.2583,,C 472 | 471,0,3,"Keefe, Mr. Arthur",male,,0,0,323592,7.25,,S 473 | 472,0,3,"Cacic, Mr. Luka",male,38,0,0,315089,8.6625,,S 474 | 473,1,2,"West, Mrs. Edwy Arthur (Ada Mary Worth)",female,33,1,2,C.A. 34651,27.75,,S 475 | 474,1,2,"Jerwan, Mrs. Amin S (Marie Marthe Thuillard)",female,23,0,0,SC/AH Basle 541,13.7917,D,C 476 | 475,0,3,"Strandberg, Miss. Ida Sofia",female,22,0,0,7553,9.8375,,S 477 | 476,0,1,"Clifford, Mr. George Quincy",male,,0,0,110465,52,A14,S 478 | 477,0,2,"Renouf, Mr. Peter Henry",male,34,1,0,31027,21,,S 479 | 478,0,3,"Braund, Mr. Lewis Richard",male,29,1,0,3460,7.0458,,S 480 | 479,0,3,"Karlsson, Mr. Nils August",male,22,0,0,350060,7.5208,,S 481 | 480,1,3,"Hirvonen, Miss. Hildur E",female,2,0,1,3101298,12.2875,,S 482 | 481,0,3,"Goodwin, Master. Harold Victor",male,9,5,2,CA 2144,46.9,,S 483 | 482,0,2,"Frost, Mr. Anthony Wood ""Archie""",male,,0,0,239854,0,,S 484 | 483,0,3,"Rouse, Mr. Richard Henry",male,50,0,0,A/5 3594,8.05,,S 485 | 484,1,3,"Turkula, Mrs. (Hedwig)",female,63,0,0,4134,9.5875,,S 486 | 485,1,1,"Bishop, Mr. Dickinson H",male,25,1,0,11967,91.0792,B49,C 487 | 486,0,3,"Lefebre, Miss. Jeannie",female,,3,1,4133,25.4667,,S 488 | 487,1,1,"Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby)",female,35,1,0,19943,90,C93,S 489 | 488,0,1,"Kent, Mr. Edward Austin",male,58,0,0,11771,29.7,B37,C 490 | 489,0,3,"Somerton, Mr. Francis William",male,30,0,0,A.5. 18509,8.05,,S 491 | 490,1,3,"Coutts, Master. Eden Leslie ""Neville""",male,9,1,1,C.A. 37671,15.9,,S 492 | 491,0,3,"Hagland, Mr. Konrad Mathias Reiersen",male,,1,0,65304,19.9667,,S 493 | 492,0,3,"Windelov, Mr. Einar",male,21,0,0,SOTON/OQ 3101317,7.25,,S 494 | 493,0,1,"Molson, Mr. Harry Markland",male,55,0,0,113787,30.5,C30,S 495 | 494,0,1,"Artagaveytia, Mr. Ramon",male,71,0,0,PC 17609,49.5042,,C 496 | 495,0,3,"Stanley, Mr. Edward Roland",male,21,0,0,A/4 45380,8.05,,S 497 | 496,0,3,"Yousseff, Mr. Gerious",male,,0,0,2627,14.4583,,C 498 | 497,1,1,"Eustis, Miss. Elizabeth Mussey",female,54,1,0,36947,78.2667,D20,C 499 | 498,0,3,"Shellard, Mr. Frederick William",male,,0,0,C.A. 6212,15.1,,S 500 | 499,0,1,"Allison, Mrs. Hudson J C (Bessie Waldo Daniels)",female,25,1,2,113781,151.55,C22 C26,S 501 | 500,0,3,"Svensson, Mr. Olof",male,24,0,0,350035,7.7958,,S 502 | 501,0,3,"Calic, Mr. Petar",male,17,0,0,315086,8.6625,,S 503 | 502,0,3,"Canavan, Miss. Mary",female,21,0,0,364846,7.75,,Q 504 | 503,0,3,"O'Sullivan, Miss. Bridget Mary",female,,0,0,330909,7.6292,,Q 505 | 504,0,3,"Laitinen, Miss. Kristina Sofia",female,37,0,0,4135,9.5875,,S 506 | 505,1,1,"Maioni, Miss. Roberta",female,16,0,0,110152,86.5,B79,S 507 | 506,0,1,"Penasco y Castellana, Mr. Victor de Satode",male,18,1,0,PC 17758,108.9,C65,C 508 | 507,1,2,"Quick, Mrs. Frederick Charles (Jane Richards)",female,33,0,2,26360,26,,S 509 | 508,1,1,"Bradley, Mr. George (""George Arthur Brayton"")",male,,0,0,111427,26.55,,S 510 | 509,0,3,"Olsen, Mr. Henry Margido",male,28,0,0,C 4001,22.525,,S 511 | 510,1,3,"Lang, Mr. Fang",male,26,0,0,1601,56.4958,,S 512 | 511,1,3,"Daly, Mr. Eugene Patrick",male,29,0,0,382651,7.75,,Q 513 | 512,0,3,"Webber, Mr. James",male,,0,0,SOTON/OQ 3101316,8.05,,S 514 | 513,1,1,"McGough, Mr. James Robert",male,36,0,0,PC 17473,26.2875,E25,S 515 | 514,1,1,"Rothschild, Mrs. Martin (Elizabeth L. Barrett)",female,54,1,0,PC 17603,59.4,,C 516 | 515,0,3,"Coleff, Mr. Satio",male,24,0,0,349209,7.4958,,S 517 | 516,0,1,"Walker, Mr. William Anderson",male,47,0,0,36967,34.0208,D46,S 518 | 517,1,2,"Lemore, Mrs. (Amelia Milley)",female,34,0,0,C.A. 34260,10.5,F33,S 519 | 518,0,3,"Ryan, Mr. Patrick",male,,0,0,371110,24.15,,Q 520 | 519,1,2,"Angle, Mrs. William A (Florence ""Mary"" Agnes Hughes)",female,36,1,0,226875,26,,S 521 | 520,0,3,"Pavlovic, Mr. Stefo",male,32,0,0,349242,7.8958,,S 522 | 521,1,1,"Perreault, Miss. Anne",female,30,0,0,12749,93.5,B73,S 523 | 522,0,3,"Vovk, Mr. Janko",male,22,0,0,349252,7.8958,,S 524 | 523,0,3,"Lahoud, Mr. Sarkis",male,,0,0,2624,7.225,,C 525 | 524,1,1,"Hippach, Mrs. Louis Albert (Ida Sophia Fischer)",female,44,0,1,111361,57.9792,B18,C 526 | 525,0,3,"Kassem, Mr. Fared",male,,0,0,2700,7.2292,,C 527 | 526,0,3,"Farrell, Mr. James",male,40.5,0,0,367232,7.75,,Q 528 | 527,1,2,"Ridsdale, Miss. Lucy",female,50,0,0,W./C. 14258,10.5,,S 529 | 528,0,1,"Farthing, Mr. John",male,,0,0,PC 17483,221.7792,C95,S 530 | 529,0,3,"Salonen, Mr. Johan Werner",male,39,0,0,3101296,7.925,,S 531 | 530,0,2,"Hocking, Mr. Richard George",male,23,2,1,29104,11.5,,S 532 | 531,1,2,"Quick, Miss. Phyllis May",female,2,1,1,26360,26,,S 533 | 532,0,3,"Toufik, Mr. Nakli",male,,0,0,2641,7.2292,,C 534 | 533,0,3,"Elias, Mr. Joseph Jr",male,17,1,1,2690,7.2292,,C 535 | 534,1,3,"Peter, Mrs. Catherine (Catherine Rizk)",female,,0,2,2668,22.3583,,C 536 | 535,0,3,"Cacic, Miss. Marija",female,30,0,0,315084,8.6625,,S 537 | 536,1,2,"Hart, Miss. Eva Miriam",female,7,0,2,F.C.C. 13529,26.25,,S 538 | 537,0,1,"Butt, Major. Archibald Willingham",male,45,0,0,113050,26.55,B38,S 539 | 538,1,1,"LeRoy, Miss. Bertha",female,30,0,0,PC 17761,106.425,,C 540 | 539,0,3,"Risien, Mr. Samuel Beard",male,,0,0,364498,14.5,,S 541 | 540,1,1,"Frolicher, Miss. Hedwig Margaritha",female,22,0,2,13568,49.5,B39,C 542 | 541,1,1,"Crosby, Miss. Harriet R",female,36,0,2,WE/P 5735,71,B22,S 543 | 542,0,3,"Andersson, Miss. Ingeborg Constanzia",female,9,4,2,347082,31.275,,S 544 | 543,0,3,"Andersson, Miss. Sigrid Elisabeth",female,11,4,2,347082,31.275,,S 545 | 544,1,2,"Beane, Mr. Edward",male,32,1,0,2908,26,,S 546 | 545,0,1,"Douglas, Mr. Walter Donald",male,50,1,0,PC 17761,106.425,C86,C 547 | 546,0,1,"Nicholson, Mr. Arthur Ernest",male,64,0,0,693,26,,S 548 | 547,1,2,"Beane, Mrs. Edward (Ethel Clarke)",female,19,1,0,2908,26,,S 549 | 548,1,2,"Padro y Manent, Mr. Julian",male,,0,0,SC/PARIS 2146,13.8625,,C 550 | 549,0,3,"Goldsmith, Mr. Frank John",male,33,1,1,363291,20.525,,S 551 | 550,1,2,"Davies, Master. John Morgan Jr",male,8,1,1,C.A. 33112,36.75,,S 552 | 551,1,1,"Thayer, Mr. John Borland Jr",male,17,0,2,17421,110.8833,C70,C 553 | 552,0,2,"Sharp, Mr. Percival James R",male,27,0,0,244358,26,,S 554 | 553,0,3,"O'Brien, Mr. Timothy",male,,0,0,330979,7.8292,,Q 555 | 554,1,3,"Leeni, Mr. Fahim (""Philip Zenni"")",male,22,0,0,2620,7.225,,C 556 | 555,1,3,"Ohman, Miss. Velin",female,22,0,0,347085,7.775,,S 557 | 556,0,1,"Wright, Mr. George",male,62,0,0,113807,26.55,,S 558 | 557,1,1,"Duff Gordon, Lady. (Lucille Christiana Sutherland) (""Mrs Morgan"")",female,48,1,0,11755,39.6,A16,C 559 | 558,0,1,"Robbins, Mr. Victor",male,,0,0,PC 17757,227.525,,C 560 | 559,1,1,"Taussig, Mrs. Emil (Tillie Mandelbaum)",female,39,1,1,110413,79.65,E67,S 561 | 560,1,3,"de Messemaeker, Mrs. Guillaume Joseph (Emma)",female,36,1,0,345572,17.4,,S 562 | 561,0,3,"Morrow, Mr. Thomas Rowan",male,,0,0,372622,7.75,,Q 563 | 562,0,3,"Sivic, Mr. Husein",male,40,0,0,349251,7.8958,,S 564 | 563,0,2,"Norman, Mr. Robert Douglas",male,28,0,0,218629,13.5,,S 565 | 564,0,3,"Simmons, Mr. John",male,,0,0,SOTON/OQ 392082,8.05,,S 566 | 565,0,3,"Meanwell, Miss. (Marion Ogden)",female,,0,0,SOTON/O.Q. 392087,8.05,,S 567 | 566,0,3,"Davies, Mr. Alfred J",male,24,2,0,A/4 48871,24.15,,S 568 | 567,0,3,"Stoytcheff, Mr. Ilia",male,19,0,0,349205,7.8958,,S 569 | 568,0,3,"Palsson, Mrs. Nils (Alma Cornelia Berglund)",female,29,0,4,349909,21.075,,S 570 | 569,0,3,"Doharr, Mr. Tannous",male,,0,0,2686,7.2292,,C 571 | 570,1,3,"Jonsson, Mr. Carl",male,32,0,0,350417,7.8542,,S 572 | 571,1,2,"Harris, Mr. George",male,62,0,0,S.W./PP 752,10.5,,S 573 | 572,1,1,"Appleton, Mrs. Edward Dale (Charlotte Lamson)",female,53,2,0,11769,51.4792,C101,S 574 | 573,1,1,"Flynn, Mr. John Irwin (""Irving"")",male,36,0,0,PC 17474,26.3875,E25,S 575 | 574,1,3,"Kelly, Miss. Mary",female,,0,0,14312,7.75,,Q 576 | 575,0,3,"Rush, Mr. Alfred George John",male,16,0,0,A/4. 20589,8.05,,S 577 | 576,0,3,"Patchett, Mr. George",male,19,0,0,358585,14.5,,S 578 | 577,1,2,"Garside, Miss. Ethel",female,34,0,0,243880,13,,S 579 | 578,1,1,"Silvey, Mrs. William Baird (Alice Munger)",female,39,1,0,13507,55.9,E44,S 580 | 579,0,3,"Caram, Mrs. Joseph (Maria Elias)",female,,1,0,2689,14.4583,,C 581 | 580,1,3,"Jussila, Mr. Eiriik",male,32,0,0,STON/O 2. 3101286,7.925,,S 582 | 581,1,2,"Christy, Miss. Julie Rachel",female,25,1,1,237789,30,,S 583 | 582,1,1,"Thayer, Mrs. John Borland (Marian Longstreth Morris)",female,39,1,1,17421,110.8833,C68,C 584 | 583,0,2,"Downton, Mr. William James",male,54,0,0,28403,26,,S 585 | 584,0,1,"Ross, Mr. John Hugo",male,36,0,0,13049,40.125,A10,C 586 | 585,0,3,"Paulner, Mr. Uscher",male,,0,0,3411,8.7125,,C 587 | 586,1,1,"Taussig, Miss. Ruth",female,18,0,2,110413,79.65,E68,S 588 | 587,0,2,"Jarvis, Mr. John Denzil",male,47,0,0,237565,15,,S 589 | 588,1,1,"Frolicher-Stehli, Mr. Maxmillian",male,60,1,1,13567,79.2,B41,C 590 | 589,0,3,"Gilinski, Mr. Eliezer",male,22,0,0,14973,8.05,,S 591 | 590,0,3,"Murdlin, Mr. Joseph",male,,0,0,A./5. 3235,8.05,,S 592 | 591,0,3,"Rintamaki, Mr. Matti",male,35,0,0,STON/O 2. 3101273,7.125,,S 593 | 592,1,1,"Stephenson, Mrs. Walter Bertram (Martha Eustis)",female,52,1,0,36947,78.2667,D20,C 594 | 593,0,3,"Elsbury, Mr. William James",male,47,0,0,A/5 3902,7.25,,S 595 | 594,0,3,"Bourke, Miss. Mary",female,,0,2,364848,7.75,,Q 596 | 595,0,2,"Chapman, Mr. John Henry",male,37,1,0,SC/AH 29037,26,,S 597 | 596,0,3,"Van Impe, Mr. Jean Baptiste",male,36,1,1,345773,24.15,,S 598 | 597,1,2,"Leitch, Miss. Jessie Wills",female,,0,0,248727,33,,S 599 | 598,0,3,"Johnson, Mr. Alfred",male,49,0,0,LINE,0,,S 600 | 599,0,3,"Boulos, Mr. Hanna",male,,0,0,2664,7.225,,C 601 | 600,1,1,"Duff Gordon, Sir. Cosmo Edmund (""Mr Morgan"")",male,49,1,0,PC 17485,56.9292,A20,C 602 | 601,1,2,"Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy)",female,24,2,1,243847,27,,S 603 | 602,0,3,"Slabenoff, Mr. Petco",male,,0,0,349214,7.8958,,S 604 | 603,0,1,"Harrington, Mr. Charles H",male,,0,0,113796,42.4,,S 605 | 604,0,3,"Torber, Mr. Ernst William",male,44,0,0,364511,8.05,,S 606 | 605,1,1,"Homer, Mr. Harry (""Mr E Haven"")",male,35,0,0,111426,26.55,,C 607 | 606,0,3,"Lindell, Mr. Edvard Bengtsson",male,36,1,0,349910,15.55,,S 608 | 607,0,3,"Karaic, Mr. Milan",male,30,0,0,349246,7.8958,,S 609 | 608,1,1,"Daniel, Mr. Robert Williams",male,27,0,0,113804,30.5,,S 610 | 609,1,2,"Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue)",female,22,1,2,SC/Paris 2123,41.5792,,C 611 | 610,1,1,"Shutes, Miss. Elizabeth W",female,40,0,0,PC 17582,153.4625,C125,S 612 | 611,0,3,"Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren)",female,39,1,5,347082,31.275,,S 613 | 612,0,3,"Jardin, Mr. Jose Neto",male,,0,0,SOTON/O.Q. 3101305,7.05,,S 614 | 613,1,3,"Murphy, Miss. Margaret Jane",female,,1,0,367230,15.5,,Q 615 | 614,0,3,"Horgan, Mr. John",male,,0,0,370377,7.75,,Q 616 | 615,0,3,"Brocklebank, Mr. William Alfred",male,35,0,0,364512,8.05,,S 617 | 616,1,2,"Herman, Miss. Alice",female,24,1,2,220845,65,,S 618 | 617,0,3,"Danbom, Mr. Ernst Gilbert",male,34,1,1,347080,14.4,,S 619 | 618,0,3,"Lobb, Mrs. William Arthur (Cordelia K Stanlick)",female,26,1,0,A/5. 3336,16.1,,S 620 | 619,1,2,"Becker, Miss. Marion Louise",female,4,2,1,230136,39,F4,S 621 | 620,0,2,"Gavey, Mr. Lawrence",male,26,0,0,31028,10.5,,S 622 | 621,0,3,"Yasbeck, Mr. Antoni",male,27,1,0,2659,14.4542,,C 623 | 622,1,1,"Kimball, Mr. Edwin Nelson Jr",male,42,1,0,11753,52.5542,D19,S 624 | 623,1,3,"Nakid, Mr. Sahid",male,20,1,1,2653,15.7417,,C 625 | 624,0,3,"Hansen, Mr. Henry Damsgaard",male,21,0,0,350029,7.8542,,S 626 | 625,0,3,"Bowen, Mr. David John ""Dai""",male,21,0,0,54636,16.1,,S 627 | 626,0,1,"Sutton, Mr. Frederick",male,61,0,0,36963,32.3208,D50,S 628 | 627,0,2,"Kirkland, Rev. Charles Leonard",male,57,0,0,219533,12.35,,Q 629 | 628,1,1,"Longley, Miss. Gretchen Fiske",female,21,0,0,13502,77.9583,D9,S 630 | 629,0,3,"Bostandyeff, Mr. Guentcho",male,26,0,0,349224,7.8958,,S 631 | 630,0,3,"O'Connell, Mr. Patrick D",male,,0,0,334912,7.7333,,Q 632 | 631,1,1,"Barkworth, Mr. Algernon Henry Wilson",male,80,0,0,27042,30,A23,S 633 | 632,0,3,"Lundahl, Mr. Johan Svensson",male,51,0,0,347743,7.0542,,S 634 | 633,1,1,"Stahelin-Maeglin, Dr. Max",male,32,0,0,13214,30.5,B50,C 635 | 634,0,1,"Parr, Mr. William Henry Marsh",male,,0,0,112052,0,,S 636 | 635,0,3,"Skoog, Miss. Mabel",female,9,3,2,347088,27.9,,S 637 | 636,1,2,"Davis, Miss. Mary",female,28,0,0,237668,13,,S 638 | 637,0,3,"Leinonen, Mr. Antti Gustaf",male,32,0,0,STON/O 2. 3101292,7.925,,S 639 | 638,0,2,"Collyer, Mr. Harvey",male,31,1,1,C.A. 31921,26.25,,S 640 | 639,0,3,"Panula, Mrs. Juha (Maria Emilia Ojala)",female,41,0,5,3101295,39.6875,,S 641 | 640,0,3,"Thorneycroft, Mr. Percival",male,,1,0,376564,16.1,,S 642 | 641,0,3,"Jensen, Mr. Hans Peder",male,20,0,0,350050,7.8542,,S 643 | 642,1,1,"Sagesser, Mlle. Emma",female,24,0,0,PC 17477,69.3,B35,C 644 | 643,0,3,"Skoog, Miss. Margit Elizabeth",female,2,3,2,347088,27.9,,S 645 | 644,1,3,"Foo, Mr. Choong",male,,0,0,1601,56.4958,,S 646 | 645,1,3,"Baclini, Miss. Eugenie",female,0.75,2,1,2666,19.2583,,C 647 | 646,1,1,"Harper, Mr. Henry Sleeper",male,48,1,0,PC 17572,76.7292,D33,C 648 | 647,0,3,"Cor, Mr. Liudevit",male,19,0,0,349231,7.8958,,S 649 | 648,1,1,"Simonius-Blumer, Col. Oberst Alfons",male,56,0,0,13213,35.5,A26,C 650 | 649,0,3,"Willey, Mr. Edward",male,,0,0,S.O./P.P. 751,7.55,,S 651 | 650,1,3,"Stanley, Miss. Amy Zillah Elsie",female,23,0,0,CA. 2314,7.55,,S 652 | 651,0,3,"Mitkoff, Mr. Mito",male,,0,0,349221,7.8958,,S 653 | 652,1,2,"Doling, Miss. Elsie",female,18,0,1,231919,23,,S 654 | 653,0,3,"Kalvik, Mr. Johannes Halvorsen",male,21,0,0,8475,8.4333,,S 655 | 654,1,3,"O'Leary, Miss. Hanora ""Norah""",female,,0,0,330919,7.8292,,Q 656 | 655,0,3,"Hegarty, Miss. Hanora ""Nora""",female,18,0,0,365226,6.75,,Q 657 | 656,0,2,"Hickman, Mr. Leonard Mark",male,24,2,0,S.O.C. 14879,73.5,,S 658 | 657,0,3,"Radeff, Mr. Alexander",male,,0,0,349223,7.8958,,S 659 | 658,0,3,"Bourke, Mrs. John (Catherine)",female,32,1,1,364849,15.5,,Q 660 | 659,0,2,"Eitemiller, Mr. George Floyd",male,23,0,0,29751,13,,S 661 | 660,0,1,"Newell, Mr. Arthur Webster",male,58,0,2,35273,113.275,D48,C 662 | 661,1,1,"Frauenthal, Dr. Henry William",male,50,2,0,PC 17611,133.65,,S 663 | 662,0,3,"Badt, Mr. Mohamed",male,40,0,0,2623,7.225,,C 664 | 663,0,1,"Colley, Mr. Edward Pomeroy",male,47,0,0,5727,25.5875,E58,S 665 | 664,0,3,"Coleff, Mr. Peju",male,36,0,0,349210,7.4958,,S 666 | 665,1,3,"Lindqvist, Mr. Eino William",male,20,1,0,STON/O 2. 3101285,7.925,,S 667 | 666,0,2,"Hickman, Mr. Lewis",male,32,2,0,S.O.C. 14879,73.5,,S 668 | 667,0,2,"Butler, Mr. Reginald Fenton",male,25,0,0,234686,13,,S 669 | 668,0,3,"Rommetvedt, Mr. Knud Paust",male,,0,0,312993,7.775,,S 670 | 669,0,3,"Cook, Mr. Jacob",male,43,0,0,A/5 3536,8.05,,S 671 | 670,1,1,"Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright)",female,,1,0,19996,52,C126,S 672 | 671,1,2,"Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford)",female,40,1,1,29750,39,,S 673 | 672,0,1,"Davidson, Mr. Thornton",male,31,1,0,F.C. 12750,52,B71,S 674 | 673,0,2,"Mitchell, Mr. Henry Michael",male,70,0,0,C.A. 24580,10.5,,S 675 | 674,1,2,"Wilhelms, Mr. Charles",male,31,0,0,244270,13,,S 676 | 675,0,2,"Watson, Mr. Ennis Hastings",male,,0,0,239856,0,,S 677 | 676,0,3,"Edvardsson, Mr. Gustaf Hjalmar",male,18,0,0,349912,7.775,,S 678 | 677,0,3,"Sawyer, Mr. Frederick Charles",male,24.5,0,0,342826,8.05,,S 679 | 678,1,3,"Turja, Miss. Anna Sofia",female,18,0,0,4138,9.8417,,S 680 | 679,0,3,"Goodwin, Mrs. Frederick (Augusta Tyler)",female,43,1,6,CA 2144,46.9,,S 681 | 680,1,1,"Cardeza, Mr. Thomas Drake Martinez",male,36,0,1,PC 17755,512.3292,B51 B53 B55,C 682 | 681,0,3,"Peters, Miss. Katie",female,,0,0,330935,8.1375,,Q 683 | 682,1,1,"Hassab, Mr. Hammad",male,27,0,0,PC 17572,76.7292,D49,C 684 | 683,0,3,"Olsvigen, Mr. Thor Anderson",male,20,0,0,6563,9.225,,S 685 | 684,0,3,"Goodwin, Mr. Charles Edward",male,14,5,2,CA 2144,46.9,,S 686 | 685,0,2,"Brown, Mr. Thomas William Solomon",male,60,1,1,29750,39,,S 687 | 686,0,2,"Laroche, Mr. Joseph Philippe Lemercier",male,25,1,2,SC/Paris 2123,41.5792,,C 688 | 687,0,3,"Panula, Mr. Jaako Arnold",male,14,4,1,3101295,39.6875,,S 689 | 688,0,3,"Dakic, Mr. Branko",male,19,0,0,349228,10.1708,,S 690 | 689,0,3,"Fischer, Mr. Eberhard Thelander",male,18,0,0,350036,7.7958,,S 691 | 690,1,1,"Madill, Miss. Georgette Alexandra",female,15,0,1,24160,211.3375,B5,S 692 | 691,1,1,"Dick, Mr. Albert Adrian",male,31,1,0,17474,57,B20,S 693 | 692,1,3,"Karun, Miss. Manca",female,4,0,1,349256,13.4167,,C 694 | 693,1,3,"Lam, Mr. Ali",male,,0,0,1601,56.4958,,S 695 | 694,0,3,"Saad, Mr. Khalil",male,25,0,0,2672,7.225,,C 696 | 695,0,1,"Weir, Col. John",male,60,0,0,113800,26.55,,S 697 | 696,0,2,"Chapman, Mr. Charles Henry",male,52,0,0,248731,13.5,,S 698 | 697,0,3,"Kelly, Mr. James",male,44,0,0,363592,8.05,,S 699 | 698,1,3,"Mullens, Miss. Katherine ""Katie""",female,,0,0,35852,7.7333,,Q 700 | 699,0,1,"Thayer, Mr. John Borland",male,49,1,1,17421,110.8833,C68,C 701 | 700,0,3,"Humblen, Mr. Adolf Mathias Nicolai Olsen",male,42,0,0,348121,7.65,F G63,S 702 | 701,1,1,"Astor, Mrs. John Jacob (Madeleine Talmadge Force)",female,18,1,0,PC 17757,227.525,C62 C64,C 703 | 702,1,1,"Silverthorne, Mr. Spencer Victor",male,35,0,0,PC 17475,26.2875,E24,S 704 | 703,0,3,"Barbara, Miss. Saiide",female,18,0,1,2691,14.4542,,C 705 | 704,0,3,"Gallagher, Mr. Martin",male,25,0,0,36864,7.7417,,Q 706 | 705,0,3,"Hansen, Mr. Henrik Juul",male,26,1,0,350025,7.8542,,S 707 | 706,0,2,"Morley, Mr. Henry Samuel (""Mr Henry Marshall"")",male,39,0,0,250655,26,,S 708 | 707,1,2,"Kelly, Mrs. Florence ""Fannie""",female,45,0,0,223596,13.5,,S 709 | 708,1,1,"Calderhead, Mr. Edward Pennington",male,42,0,0,PC 17476,26.2875,E24,S 710 | 709,1,1,"Cleaver, Miss. Alice",female,22,0,0,113781,151.55,,S 711 | 710,1,3,"Moubarek, Master. Halim Gonios (""William George"")",male,,1,1,2661,15.2458,,C 712 | 711,1,1,"Mayne, Mlle. Berthe Antonine (""Mrs de Villiers"")",female,24,0,0,PC 17482,49.5042,C90,C 713 | 712,0,1,"Klaber, Mr. Herman",male,,0,0,113028,26.55,C124,S 714 | 713,1,1,"Taylor, Mr. Elmer Zebley",male,48,1,0,19996,52,C126,S 715 | 714,0,3,"Larsson, Mr. August Viktor",male,29,0,0,7545,9.4833,,S 716 | 715,0,2,"Greenberg, Mr. Samuel",male,52,0,0,250647,13,,S 717 | 716,0,3,"Soholt, Mr. Peter Andreas Lauritz Andersen",male,19,0,0,348124,7.65,F G73,S 718 | 717,1,1,"Endres, Miss. Caroline Louise",female,38,0,0,PC 17757,227.525,C45,C 719 | 718,1,2,"Troutt, Miss. Edwina Celia ""Winnie""",female,27,0,0,34218,10.5,E101,S 720 | 719,0,3,"McEvoy, Mr. Michael",male,,0,0,36568,15.5,,Q 721 | 720,0,3,"Johnson, Mr. Malkolm Joackim",male,33,0,0,347062,7.775,,S 722 | 721,1,2,"Harper, Miss. Annie Jessie ""Nina""",female,6,0,1,248727,33,,S 723 | 722,0,3,"Jensen, Mr. Svend Lauritz",male,17,1,0,350048,7.0542,,S 724 | 723,0,2,"Gillespie, Mr. William Henry",male,34,0,0,12233,13,,S 725 | 724,0,2,"Hodges, Mr. Henry Price",male,50,0,0,250643,13,,S 726 | 725,1,1,"Chambers, Mr. Norman Campbell",male,27,1,0,113806,53.1,E8,S 727 | 726,0,3,"Oreskovic, Mr. Luka",male,20,0,0,315094,8.6625,,S 728 | 727,1,2,"Renouf, Mrs. Peter Henry (Lillian Jefferys)",female,30,3,0,31027,21,,S 729 | 728,1,3,"Mannion, Miss. Margareth",female,,0,0,36866,7.7375,,Q 730 | 729,0,2,"Bryhl, Mr. Kurt Arnold Gottfrid",male,25,1,0,236853,26,,S 731 | 730,0,3,"Ilmakangas, Miss. Pieta Sofia",female,25,1,0,STON/O2. 3101271,7.925,,S 732 | 731,1,1,"Allen, Miss. Elisabeth Walton",female,29,0,0,24160,211.3375,B5,S 733 | 732,0,3,"Hassan, Mr. Houssein G N",male,11,0,0,2699,18.7875,,C 734 | 733,0,2,"Knight, Mr. Robert J",male,,0,0,239855,0,,S 735 | 734,0,2,"Berriman, Mr. William John",male,23,0,0,28425,13,,S 736 | 735,0,2,"Troupiansky, Mr. Moses Aaron",male,23,0,0,233639,13,,S 737 | 736,0,3,"Williams, Mr. Leslie",male,28.5,0,0,54636,16.1,,S 738 | 737,0,3,"Ford, Mrs. Edward (Margaret Ann Watson)",female,48,1,3,W./C. 6608,34.375,,S 739 | 738,1,1,"Lesurer, Mr. Gustave J",male,35,0,0,PC 17755,512.3292,B101,C 740 | 739,0,3,"Ivanoff, Mr. Kanio",male,,0,0,349201,7.8958,,S 741 | 740,0,3,"Nankoff, Mr. Minko",male,,0,0,349218,7.8958,,S 742 | 741,1,1,"Hawksford, Mr. Walter James",male,,0,0,16988,30,D45,S 743 | 742,0,1,"Cavendish, Mr. Tyrell William",male,36,1,0,19877,78.85,C46,S 744 | 743,1,1,"Ryerson, Miss. Susan Parker ""Suzette""",female,21,2,2,PC 17608,262.375,B57 B59 B63 B66,C 745 | 744,0,3,"McNamee, Mr. Neal",male,24,1,0,376566,16.1,,S 746 | 745,1,3,"Stranden, Mr. Juho",male,31,0,0,STON/O 2. 3101288,7.925,,S 747 | 746,0,1,"Crosby, Capt. Edward Gifford",male,70,1,1,WE/P 5735,71,B22,S 748 | 747,0,3,"Abbott, Mr. Rossmore Edward",male,16,1,1,C.A. 2673,20.25,,S 749 | 748,1,2,"Sinkkonen, Miss. Anna",female,30,0,0,250648,13,,S 750 | 749,0,1,"Marvin, Mr. Daniel Warner",male,19,1,0,113773,53.1,D30,S 751 | 750,0,3,"Connaghton, Mr. Michael",male,31,0,0,335097,7.75,,Q 752 | 751,1,2,"Wells, Miss. Joan",female,4,1,1,29103,23,,S 753 | 752,1,3,"Moor, Master. Meier",male,6,0,1,392096,12.475,E121,S 754 | 753,0,3,"Vande Velde, Mr. Johannes Joseph",male,33,0,0,345780,9.5,,S 755 | 754,0,3,"Jonkoff, Mr. Lalio",male,23,0,0,349204,7.8958,,S 756 | 755,1,2,"Herman, Mrs. Samuel (Jane Laver)",female,48,1,2,220845,65,,S 757 | 756,1,2,"Hamalainen, Master. Viljo",male,0.67,1,1,250649,14.5,,S 758 | 757,0,3,"Carlsson, Mr. August Sigfrid",male,28,0,0,350042,7.7958,,S 759 | 758,0,2,"Bailey, Mr. Percy Andrew",male,18,0,0,29108,11.5,,S 760 | 759,0,3,"Theobald, Mr. Thomas Leonard",male,34,0,0,363294,8.05,,S 761 | 760,1,1,"Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards)",female,33,0,0,110152,86.5,B77,S 762 | 761,0,3,"Garfirth, Mr. John",male,,0,0,358585,14.5,,S 763 | 762,0,3,"Nirva, Mr. Iisakki Antino Aijo",male,41,0,0,SOTON/O2 3101272,7.125,,S 764 | 763,1,3,"Barah, Mr. Hanna Assi",male,20,0,0,2663,7.2292,,C 765 | 764,1,1,"Carter, Mrs. William Ernest (Lucile Polk)",female,36,1,2,113760,120,B96 B98,S 766 | 765,0,3,"Eklund, Mr. Hans Linus",male,16,0,0,347074,7.775,,S 767 | 766,1,1,"Hogeboom, Mrs. John C (Anna Andrews)",female,51,1,0,13502,77.9583,D11,S 768 | 767,0,1,"Brewe, Dr. Arthur Jackson",male,,0,0,112379,39.6,,C 769 | 768,0,3,"Mangan, Miss. Mary",female,30.5,0,0,364850,7.75,,Q 770 | 769,0,3,"Moran, Mr. Daniel J",male,,1,0,371110,24.15,,Q 771 | 770,0,3,"Gronnestad, Mr. Daniel Danielsen",male,32,0,0,8471,8.3625,,S 772 | 771,0,3,"Lievens, Mr. Rene Aime",male,24,0,0,345781,9.5,,S 773 | 772,0,3,"Jensen, Mr. Niels Peder",male,48,0,0,350047,7.8542,,S 774 | 773,0,2,"Mack, Mrs. (Mary)",female,57,0,0,S.O./P.P. 3,10.5,E77,S 775 | 774,0,3,"Elias, Mr. Dibo",male,,0,0,2674,7.225,,C 776 | 775,1,2,"Hocking, Mrs. Elizabeth (Eliza Needs)",female,54,1,3,29105,23,,S 777 | 776,0,3,"Myhrman, Mr. Pehr Fabian Oliver Malkolm",male,18,0,0,347078,7.75,,S 778 | 777,0,3,"Tobin, Mr. Roger",male,,0,0,383121,7.75,F38,Q 779 | 778,1,3,"Emanuel, Miss. Virginia Ethel",female,5,0,0,364516,12.475,,S 780 | 779,0,3,"Kilgannon, Mr. Thomas J",male,,0,0,36865,7.7375,,Q 781 | 780,1,1,"Robert, Mrs. Edward Scott (Elisabeth Walton McMillan)",female,43,0,1,24160,211.3375,B3,S 782 | 781,1,3,"Ayoub, Miss. Banoura",female,13,0,0,2687,7.2292,,C 783 | 782,1,1,"Dick, Mrs. Albert Adrian (Vera Gillespie)",female,17,1,0,17474,57,B20,S 784 | 783,0,1,"Long, Mr. Milton Clyde",male,29,0,0,113501,30,D6,S 785 | 784,0,3,"Johnston, Mr. Andrew G",male,,1,2,W./C. 6607,23.45,,S 786 | 785,0,3,"Ali, Mr. William",male,25,0,0,SOTON/O.Q. 3101312,7.05,,S 787 | 786,0,3,"Harmer, Mr. Abraham (David Lishin)",male,25,0,0,374887,7.25,,S 788 | 787,1,3,"Sjoblom, Miss. Anna Sofia",female,18,0,0,3101265,7.4958,,S 789 | 788,0,3,"Rice, Master. George Hugh",male,8,4,1,382652,29.125,,Q 790 | 789,1,3,"Dean, Master. Bertram Vere",male,1,1,2,C.A. 2315,20.575,,S 791 | 790,0,1,"Guggenheim, Mr. Benjamin",male,46,0,0,PC 17593,79.2,B82 B84,C 792 | 791,0,3,"Keane, Mr. Andrew ""Andy""",male,,0,0,12460,7.75,,Q 793 | 792,0,2,"Gaskell, Mr. Alfred",male,16,0,0,239865,26,,S 794 | 793,0,3,"Sage, Miss. Stella Anna",female,,8,2,CA. 2343,69.55,,S 795 | 794,0,1,"Hoyt, Mr. William Fisher",male,,0,0,PC 17600,30.6958,,C 796 | 795,0,3,"Dantcheff, Mr. Ristiu",male,25,0,0,349203,7.8958,,S 797 | 796,0,2,"Otter, Mr. Richard",male,39,0,0,28213,13,,S 798 | 797,1,1,"Leader, Dr. Alice (Farnham)",female,49,0,0,17465,25.9292,D17,S 799 | 798,1,3,"Osman, Mrs. Mara",female,31,0,0,349244,8.6833,,S 800 | 799,0,3,"Ibrahim Shawah, Mr. Yousseff",male,30,0,0,2685,7.2292,,C 801 | 800,0,3,"Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert)",female,30,1,1,345773,24.15,,S 802 | 801,0,2,"Ponesell, Mr. Martin",male,34,0,0,250647,13,,S 803 | 802,1,2,"Collyer, Mrs. Harvey (Charlotte Annie Tate)",female,31,1,1,C.A. 31921,26.25,,S 804 | 803,1,1,"Carter, Master. William Thornton II",male,11,1,2,113760,120,B96 B98,S 805 | 804,1,3,"Thomas, Master. Assad Alexander",male,0.42,0,1,2625,8.5167,,C 806 | 805,1,3,"Hedman, Mr. Oskar Arvid",male,27,0,0,347089,6.975,,S 807 | 806,0,3,"Johansson, Mr. Karl Johan",male,31,0,0,347063,7.775,,S 808 | 807,0,1,"Andrews, Mr. Thomas Jr",male,39,0,0,112050,0,A36,S 809 | 808,0,3,"Pettersson, Miss. Ellen Natalia",female,18,0,0,347087,7.775,,S 810 | 809,0,2,"Meyer, Mr. August",male,39,0,0,248723,13,,S 811 | 810,1,1,"Chambers, Mrs. Norman Campbell (Bertha Griggs)",female,33,1,0,113806,53.1,E8,S 812 | 811,0,3,"Alexander, Mr. William",male,26,0,0,3474,7.8875,,S 813 | 812,0,3,"Lester, Mr. James",male,39,0,0,A/4 48871,24.15,,S 814 | 813,0,2,"Slemen, Mr. Richard James",male,35,0,0,28206,10.5,,S 815 | 814,0,3,"Andersson, Miss. Ebba Iris Alfrida",female,6,4,2,347082,31.275,,S 816 | 815,0,3,"Tomlin, Mr. Ernest Portage",male,30.5,0,0,364499,8.05,,S 817 | 816,0,1,"Fry, Mr. Richard",male,,0,0,112058,0,B102,S 818 | 817,0,3,"Heininen, Miss. Wendla Maria",female,23,0,0,STON/O2. 3101290,7.925,,S 819 | 818,0,2,"Mallet, Mr. Albert",male,31,1,1,S.C./PARIS 2079,37.0042,,C 820 | 819,0,3,"Holm, Mr. John Fredrik Alexander",male,43,0,0,C 7075,6.45,,S 821 | 820,0,3,"Skoog, Master. Karl Thorsten",male,10,3,2,347088,27.9,,S 822 | 821,1,1,"Hays, Mrs. Charles Melville (Clara Jennings Gregg)",female,52,1,1,12749,93.5,B69,S 823 | 822,1,3,"Lulic, Mr. Nikola",male,27,0,0,315098,8.6625,,S 824 | 823,0,1,"Reuchlin, Jonkheer. John George",male,38,0,0,19972,0,,S 825 | 824,1,3,"Moor, Mrs. (Beila)",female,27,0,1,392096,12.475,E121,S 826 | 825,0,3,"Panula, Master. Urho Abraham",male,2,4,1,3101295,39.6875,,S 827 | 826,0,3,"Flynn, Mr. John",male,,0,0,368323,6.95,,Q 828 | 827,0,3,"Lam, Mr. Len",male,,0,0,1601,56.4958,,S 829 | 828,1,2,"Mallet, Master. Andre",male,1,0,2,S.C./PARIS 2079,37.0042,,C 830 | 829,1,3,"McCormack, Mr. Thomas Joseph",male,,0,0,367228,7.75,,Q 831 | 830,1,1,"Stone, Mrs. George Nelson (Martha Evelyn)",female,62,0,0,113572,80,B28, 832 | 831,1,3,"Yasbeck, Mrs. Antoni (Selini Alexander)",female,15,1,0,2659,14.4542,,C 833 | 832,1,2,"Richards, Master. George Sibley",male,0.83,1,1,29106,18.75,,S 834 | 833,0,3,"Saad, Mr. Amin",male,,0,0,2671,7.2292,,C 835 | 834,0,3,"Augustsson, Mr. Albert",male,23,0,0,347468,7.8542,,S 836 | 835,0,3,"Allum, Mr. Owen George",male,18,0,0,2223,8.3,,S 837 | 836,1,1,"Compton, Miss. Sara Rebecca",female,39,1,1,PC 17756,83.1583,E49,C 838 | 837,0,3,"Pasic, Mr. Jakob",male,21,0,0,315097,8.6625,,S 839 | 838,0,3,"Sirota, Mr. Maurice",male,,0,0,392092,8.05,,S 840 | 839,1,3,"Chip, Mr. Chang",male,32,0,0,1601,56.4958,,S 841 | 840,1,1,"Marechal, Mr. Pierre",male,,0,0,11774,29.7,C47,C 842 | 841,0,3,"Alhomaki, Mr. Ilmari Rudolf",male,20,0,0,SOTON/O2 3101287,7.925,,S 843 | 842,0,2,"Mudd, Mr. Thomas Charles",male,16,0,0,S.O./P.P. 3,10.5,,S 844 | 843,1,1,"Serepeca, Miss. Augusta",female,30,0,0,113798,31,,C 845 | 844,0,3,"Lemberopolous, Mr. Peter L",male,34.5,0,0,2683,6.4375,,C 846 | 845,0,3,"Culumovic, Mr. Jeso",male,17,0,0,315090,8.6625,,S 847 | 846,0,3,"Abbing, Mr. Anthony",male,42,0,0,C.A. 5547,7.55,,S 848 | 847,0,3,"Sage, Mr. Douglas Bullen",male,,8,2,CA. 2343,69.55,,S 849 | 848,0,3,"Markoff, Mr. Marin",male,35,0,0,349213,7.8958,,C 850 | 849,0,2,"Harper, Rev. John",male,28,0,1,248727,33,,S 851 | 850,1,1,"Goldenberg, Mrs. Samuel L (Edwiga Grabowska)",female,,1,0,17453,89.1042,C92,C 852 | 851,0,3,"Andersson, Master. Sigvard Harald Elias",male,4,4,2,347082,31.275,,S 853 | 852,0,3,"Svensson, Mr. Johan",male,74,0,0,347060,7.775,,S 854 | 853,0,3,"Boulos, Miss. Nourelain",female,9,1,1,2678,15.2458,,C 855 | 854,1,1,"Lines, Miss. Mary Conover",female,16,0,1,PC 17592,39.4,D28,S 856 | 855,0,2,"Carter, Mrs. Ernest Courtenay (Lilian Hughes)",female,44,1,0,244252,26,,S 857 | 856,1,3,"Aks, Mrs. Sam (Leah Rosen)",female,18,0,1,392091,9.35,,S 858 | 857,1,1,"Wick, Mrs. George Dennick (Mary Hitchcock)",female,45,1,1,36928,164.8667,,S 859 | 858,1,1,"Daly, Mr. Peter Denis ",male,51,0,0,113055,26.55,E17,S 860 | 859,1,3,"Baclini, Mrs. Solomon (Latifa Qurban)",female,24,0,3,2666,19.2583,,C 861 | 860,0,3,"Razi, Mr. Raihed",male,,0,0,2629,7.2292,,C 862 | 861,0,3,"Hansen, Mr. Claus Peter",male,41,2,0,350026,14.1083,,S 863 | 862,0,2,"Giles, Mr. Frederick Edward",male,21,1,0,28134,11.5,,S 864 | 863,1,1,"Swift, Mrs. Frederick Joel (Margaret Welles Barron)",female,48,0,0,17466,25.9292,D17,S 865 | 864,0,3,"Sage, Miss. Dorothy Edith ""Dolly""",female,,8,2,CA. 2343,69.55,,S 866 | 865,0,2,"Gill, Mr. John William",male,24,0,0,233866,13,,S 867 | 866,1,2,"Bystrom, Mrs. (Karolina)",female,42,0,0,236852,13,,S 868 | 867,1,2,"Duran y More, Miss. Asuncion",female,27,1,0,SC/PARIS 2149,13.8583,,C 869 | 868,0,1,"Roebling, Mr. Washington Augustus II",male,31,0,0,PC 17590,50.4958,A24,S 870 | 869,0,3,"van Melkebeke, Mr. Philemon",male,,0,0,345777,9.5,,S 871 | 870,1,3,"Johnson, Master. Harold Theodor",male,4,1,1,347742,11.1333,,S 872 | 871,0,3,"Balkic, Mr. Cerin",male,26,0,0,349248,7.8958,,S 873 | 872,1,1,"Beckwith, Mrs. Richard Leonard (Sallie Monypeny)",female,47,1,1,11751,52.5542,D35,S 874 | 873,0,1,"Carlsson, Mr. Frans Olof",male,33,0,0,695,5,B51 B53 B55,S 875 | 874,0,3,"Vander Cruyssen, Mr. Victor",male,47,0,0,345765,9,,S 876 | 875,1,2,"Abelson, Mrs. Samuel (Hannah Wizosky)",female,28,1,0,P/PP 3381,24,,C 877 | 876,1,3,"Najib, Miss. Adele Kiamie ""Jane""",female,15,0,0,2667,7.225,,C 878 | 877,0,3,"Gustafsson, Mr. Alfred Ossian",male,20,0,0,7534,9.8458,,S 879 | 878,0,3,"Petroff, Mr. Nedelio",male,19,0,0,349212,7.8958,,S 880 | 879,0,3,"Laleff, Mr. Kristo",male,,0,0,349217,7.8958,,S 881 | 880,1,1,"Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)",female,56,0,1,11767,83.1583,C50,C 882 | 881,1,2,"Shelley, Mrs. William (Imanita Parrish Hall)",female,25,0,1,230433,26,,S 883 | 882,0,3,"Markun, Mr. Johann",male,33,0,0,349257,7.8958,,S 884 | 883,0,3,"Dahlberg, Miss. Gerda Ulrika",female,22,0,0,7552,10.5167,,S 885 | 884,0,2,"Banfield, Mr. Frederick James",male,28,0,0,C.A./SOTON 34068,10.5,,S 886 | 885,0,3,"Sutehall, Mr. Henry Jr",male,25,0,0,SOTON/OQ 392076,7.05,,S 887 | 886,0,3,"Rice, Mrs. William (Margaret Norton)",female,39,0,5,382652,29.125,,Q 888 | 887,0,2,"Montvila, Rev. Juozas",male,27,0,0,211536,13,,S 889 | 888,1,1,"Graham, Miss. Margaret Edith",female,19,0,0,112053,30,B42,S 890 | 889,0,3,"Johnston, Miss. Catherine Helen ""Carrie""",female,,1,2,W./C. 6607,23.45,,S 891 | 890,1,1,"Behr, Mr. Karl Howell",male,26,0,0,111369,30,C148,C 892 | 891,0,3,"Dooley, Mr. Patrick",male,32,0,0,370376,7.75,,Q 893 | -------------------------------------------------------------------------------- /easyML/tests/test_preprocess.py: -------------------------------------------------------------------------------- 1 | ##################################################################### 2 | ##### IMPORT STANDARD MODULES 3 | ##################################################################### 4 | 5 | from __future__ import print_function 6 | 7 | from ..data import DataBlock 8 | 9 | from ..preprocess import PreProcess 10 | 11 | import pandas as pd 12 | import numpy as np 13 | from sklearn.datasets import load_iris 14 | from random import sample 15 | 16 | ##################################################################### 17 | ##### TESTS FOR DATABLOCK 18 | ##################################################################### 19 | 20 | def test_datablock(datablock): 21 | assert datablock.train.shape == (150, 5) 22 | assert datablock.test.shape == (150, 5) 23 | assert datablock.predict.shape == (150, 5) 24 | 25 | ##################################################################### 26 | ##### TESTS FOR PREPROCESS 27 | ##################################################################### 28 | 29 | def test_check_missing_no_missing(datablock): 30 | pp = PreProcess(datablock) 31 | result = pp.check_missing(printResult=False,returnResult=True) 32 | for df,miss in result.items(): 33 | print(df,miss) 34 | assert miss.sum()==0 35 | 36 | def test_check_missing_missing_induced(datablock): 37 | df = pd.DataFrame(datablock.train,copy=True) 38 | pp = PreProcess(DataBlock(df,df,df,'target')) 39 | num_miss=25 40 | for data in pp.datablock.data_present().values(): 41 | data.iloc[sample(range(150),num_miss),0] = np.nan 42 | result = pp.check_missing(printResult=False,returnResult=True) 43 | for key,miss in result.items(): 44 | assert miss.sum()==num_miss 45 | 46 | -------------------------------------------------------------------------------- /examples/README.txt: -------------------------------------------------------------------------------- 1 | .. _general_examples: 2 | 3 | General examples 4 | ================ 5 | 6 | Introductory examples coming up soon. 7 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | numpy>=1.11.3 2 | pandas>=0.19.2 3 | pyparsing>=2.1.10 4 | scipy>=0.18.1 5 | scikit-learn>=0.18 -------------------------------------------------------------------------------- /requirements_dev.txt: -------------------------------------------------------------------------------- 1 | coverage==4.3.1 2 | pandas==0.19.2 3 | pytest==3.0.5 4 | pytest-cov==2.4.0 5 | requests==2.12.4 6 | scikit-learn==0.18.1 -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [metadata] 2 | description-file = README.md 3 | 4 | [bdist_wheel] 5 | #This flag says that the code is written to work on both Python 2 and Python 3 6 | universal=1 -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from __future__ import print_function 2 | import sys 3 | from setuptools import setup, find_packages 4 | 5 | with open('requirements.txt') as f: 6 | INSTALL_REQUIRES = [l.strip() for l in f.readlines() if l] 7 | 8 | with open('requirements_dev.txt') as f: 9 | TEST_REQUIRES = [l.strip() for l in f.readlines() if l] 10 | 11 | with open('README.md') as readme_file: 12 | readme = readme_file.read() 13 | 14 | try: 15 | import numpy 16 | except ImportError: 17 | print('numpy is required during installation') 18 | sys.exit(1) 19 | 20 | try: 21 | import scipy 22 | except ImportError: 23 | print('scipy is required during installation') 24 | sys.exit(1) 25 | 26 | setup(name='easyML', 27 | version='0.1.0', 28 | description='A package designed to streamline the process of analyzing data using predictive models from scikit-learn\'s implementation.', 29 | long_description=readme, 30 | author='Aarshay Jain', 31 | license='BSD', 32 | packages=find_packages(), 33 | install_requires=INSTALL_REQUIRES, 34 | author_email='aarshay.jain@columbia.edu', 35 | url='https://github.com/aarshayj/easyML', 36 | classifiers=[ 37 | 'Development Status :: 3 - Alpha', 38 | 'Environment :: Console', 39 | 'Intended Audience :: Science/Research', 40 | 'Intended Audience :: Education', 41 | 'Natural Language :: English', 42 | 'License :: OSI Approved :: BSD License', 43 | 'Programming Language :: Python', 44 | 'Programming Language :: Python :: 2.7', 45 | 'Programming Language :: Python :: 3.4', 46 | 'Programming Language :: Python :: 3.5', 47 | 'Topic :: Scientific/Engineering :: Information Analysis', 48 | 'Topic :: Software Development :: Libraries :: Python Modules' 49 | ], 50 | test_suite='tests', 51 | tests_require=TEST_REQUIRES 52 | ) 53 | --------------------------------------------------------------------------------