{ "cells": [ { "cell_type": "markdown", "metadata": { "toc": true }, "source": [ "

Table of Contents

\n", "
" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "" ], "text/plain": [ "" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# code for loading the format for the notebook\n", "import os\n", "\n", "# path : store the current path to convert back to it later\n", "path = os.getcwd()\n", "os.chdir(os.path.join('..', '..', 'notebook_format'))\n", "\n", "from formats import load_style\n", "load_style(css_style = 'custom2.css', plot_style = False)" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "os.chdir(path)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Data Science is Software" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Developer life hacks for Data Scientist." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Section 1: Environment Reproducibility" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### [watermark](https://github.com/rasbt/watermark) extension\n", "\n", "Tell everyone when you ran the notebook, and packages' version that you were using. Listing these dependency information at the top of a notebook is especially useful for nbviewer, blog posts and other media where you are not sharing the notebook as executable code." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Ethen 2018-09-17 21:32:12 \n", "\n", "CPython 3.6.4\n", "IPython 6.4.0\n", "\n", "numpy 1.14.1\n", "pandas 0.23.0\n", "seaborn 0.8.1\n", "watermark 1.6.0\n", "matplotlib 2.2.2\n" ] } ], "source": [ "# once it is installed, we'll just need this in future notebooks:\n", "%load_ext watermark\n", "%watermark -a \"Ethen\" -d -t -v -p numpy,pandas,seaborn,watermark,matplotlib" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here, we're only importing the watermark extension, but it's also a good idea to do all of our other imports at the first cell of the notebook.\n", "\n", "### Create A Separate Environment\n", "\n", "Continuum's `conda` tool provides a way to create [isolated environments](http://conda.pydata.org/docs/using/envs.html). The `conda env` functionality let's you created an isolated environment on your machine, that way we can \n", "\n", "- Start from \"scratch\" on each project\n", "- Choose Python 2 or 3 as appropriate\n", "\n", "To create an empty environment:\n", "\n", "- `conda create -n python=3`\n", "\n", "**Note: `python=2` will create a Python 2 environment; `python=3` will create a Python 3 environment.**\n", "\n", "To work in a particular virtual environment:\n", "\n", "- `source activate `\n", " \n", "To leave a virtual environment:\n", "\n", "- `source deactivate`\n", "\n", "**Note: on Windows, the commands are just `activate` and `deactivate`, no need to type `source`.**\n", "\n", "There are other Python tools for environment isolation, but none of them are perfect. If you're interested in the other options, [`virtualenv`](https://virtualenv.pypa.io/en/stable/) and [`pyenv`](https://github.com/yyuu/pyenv) both provide environment isolation. There are _sometimes_ compatibility issues between the Anaconda Python distribution and these packages, so if you've got Anaconda on your machine you can use `conda env` to create and manage environments.\n", "\n", "

\n", "

\n", "\n", "Create a new environment for every project you work on\n", "\n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### The pip [requirements.txt](https://pip.readthedocs.org/en/1.1/requirements.html) file\n", "\n", "It's a convention in the Python ecosystem to track a project's dependencies in a file called `requirements.txt`. We recommend using this file to keep track of your MRE, \"Minimum reproducible environment\". An example of `requirements.txt` might look something like the following:\n", "\n", "```text\n", "pandas>=0.19.2\n", "matplotlib>=2.0.0\n", "```\n", "\n", "The format for a line in the requirements file is:\n", "\n", " | Syntax | Result |\n", " | --- | --- |\n", " | `package_name` | for whatever the latest version on PyPI is |\n", " | `package_name==X.X.X` | for an exact match of version X.X.X |\n", " | `package_name>=X.X.X` | for at least version X.X.X |\n", " \n", "Now, contributors can create a new virtual environment (using conda or any other tool) and install your dependencies just by running:\n", "\n", "`pip install -r requirements.txt`\n", " \n", "

\n", "

\n", "Never again run `pip install [package]`. Instead, update `requirements.txt` and run `pip install -r requirements.txt`. And for data science projects, favor `package>=0.0.0` rather than `package==0.0.0`, this prevents you from having many versions of large packages (e.g. numpy, scipy, pandas) with complex dependencies sitting around\n", "
\n", "\n", "Usually the package version will adhere to [semantic versioning](http://semver.org/). Let’s take 0.19.2 as an example and break down what each number represents.\n", "\n", "- (**0**.19.2) The first number in this chain is called the major version.\n", "- (0.**19**.2) The second number is called the minor version.\n", "- (0.19.**2**) The third number is called the patch version.\n", "\n", "These versions are incremented when code changes are introduced. Depending on the nature of the change, a different number is incremented.\n", "\n", "- The major version (first number) is incremented when there's backwards incompatible changes, i.e. changes that break the old API are released. Usually, when major versions are released there’s a guide released with how to update from the old version to the new one\n", "- The minor version (second number) is incremented when backwards compatible changes. Functionality is added (or speed improvements) that does not break any existing functionality, at least the public API that end-users would use\n", "- The patch version (third number) is for backwards compatible bug fixes. Bug fixes are in contrast here with features (adding functionality). These patches go out when something is wrong with existing functionality or when improvements to existing functionality are implemented\n", "\n", "\n", "Both the `requirements.txt` file and `conda` virtual environment are ways to isoloate each project's environment and dependencies so we or other people that are trying to reproduce our work can save a lot of time recreating the environment." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Separation of configuration from codebase\n", "\n", "There are some things you don't want to be openly reproducible: your private database url, your AWS credentials for downloading the data, your SSN, which you decided to use as a hash. These shouldn't live in source control, but may be essential for collaborators or others reproducing your work.\n", "\n", "This is a situation where we can learn from some software engineering best practices. The [12-factor app principles](http://12factor.net/) give a set of best-practices for building web applications. Many of these principles are relevant for best practices in the data-science codebases as well.\n", "\n", "Using a dependency manifest like `requirements.txt` satisfies [II. Explicitly declare and isolate dependencies](http://12factor.net/dependencies). Another important principle is [III. Store config in the environment](http://12factor.net/config):\n", "\n", " > An app’s config is everything that is likely to vary between deploys (staging, production, developer environments, etc). Apps sometimes store config as constants in the code. This is a violation of twelve-factor, which requires strict separation of config from code. Config varies substantially across deploys, code does not. A litmus test for whether an app has all config correctly factored out of the code is whether the codebase could be made open source at any moment, without compromising any credentials.\n", " \n", "The [`dotenv` package](https://github.com/theskumar/python-dotenv) allows you to easily store these variables in a file that is not in source control (as long as you keep the line `.env` in your `.gitignore` file!). You can then reference these variables as environment variables in your application with `os.environ.get('VARIABLE_NAME')`." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "import os\n", "from dotenv import load_dotenv" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# load the .env file\n", "load_dotenv('.env')" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# obtain the value of the variable\n", "os.environ.get('FOO')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Note that there's also [configparser](https://docs.python.org/3/library/configparser.html)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Section 2: Writing code for reusability" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "If the code prints out some output and we want the reader to see it within some context (e.g. presenting a data story), then jupyter notebook it a ideal place for it to live. However, we wish to use the same piece of code in multiple notebooks then we should save it to a standalone `.py` file to prevent copying and pasting the same piece of code every single time. Finally, if the code is going to used in multiple data analysis project then we should consider creating a package for it.\n", "\n", "### No more docs-guessing\n", "\n", "Don't edit-run-repeat to try to remember the name of a function or argument. Jupyter provides great docs integration and easy ways to remember the arguments to a function.\n", "\n", "> To check the doc, we can simply add a question mark `?` after the method, or press `Shift Tab` (press both at the same time) inside the bracket of the method and it will print out argument to the method. Also the `Tab` key can be used for auto-completion of methods and arguments for a method.\n", "\n", "Consider the following example. To follow along, please download the dataset `pumps_train_values.csv` from the following [link](https://github.com/drivendata/data-science-is-software/tree/master/data/raw) and move it to the `../data/raw` file path, or change the `pump_data_path` below to where you like to store it." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idamount_tshdate_recordedfundergps_heightinstallerlongitudelatitudewpt_namenum_private...payment_typewater_qualityquality_groupquantityquantity_groupsourcesource_typesource_classwaterpoint_typewaterpoint_type_group
0695726000.02011-03-14Roman1390Roman34.938093-9.856322none0...annuallysoftgoodenoughenoughspringspringgroundwatercommunal standpipecommunal standpipe
\n", "

1 rows × 40 columns

\n", "
" ], "text/plain": [ " id amount_tsh date_recorded funder gps_height installer longitude \\\n", "0 69572 6000.0 2011-03-14 Roman 1390 Roman 34.938093 \n", "\n", " latitude wpt_name num_private ... payment_type \\\n", "0 -9.856322 none 0 ... annually \n", "\n", " water_quality quality_group quantity quantity_group source source_type \\\n", "0 soft good enough enough spring spring \n", "\n", " source_class waterpoint_type waterpoint_type_group \n", "0 groundwater communal standpipe communal standpipe \n", "\n", "[1 rows x 40 columns]" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import os\n", "import pandas as pd\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "\n", "pump_data_path = os.path.join('..', 'data', 'raw', 'pumps_train_values.csv')\n", "df = pd.read_csv(pump_data_path)\n", "df.head(1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "After reading in the data, we discovered that the data provides an `id` column and we wish to change it to the index column. But we forgot the parameter to do so." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
amount_tshdate_recordedfundergps_heightinstallerlongitudelatitudewpt_namenum_privatebasin...payment_typewater_qualityquality_groupquantityquantity_groupsourcesource_typesource_classwaterpoint_typewaterpoint_type_group
id
695726000.02011-03-14Roman1390Roman34.938093-9.856322none0Lake Nyasa...annuallysoftgoodenoughenoughspringspringgroundwatercommunal standpipecommunal standpipe
\n", "

1 rows × 39 columns

\n", "
" ], "text/plain": [ " amount_tsh date_recorded funder gps_height installer longitude \\\n", "id \n", "69572 6000.0 2011-03-14 Roman 1390 Roman 34.938093 \n", "\n", " latitude wpt_name num_private basin ... \\\n", "id ... \n", "69572 -9.856322 none 0 Lake Nyasa ... \n", "\n", " payment_type water_quality quality_group quantity quantity_group \\\n", "id \n", "69572 annually soft good enough enough \n", "\n", " source source_type source_class waterpoint_type \\\n", "id \n", "69572 spring spring groundwater communal standpipe \n", "\n", " waterpoint_type_group \n", "id \n", "69572 communal standpipe \n", "\n", "[1 rows x 39 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# we can do ?pd.read_csv or just check the \n", "# documentation online since it usually looks nicer ...\n", "df = pd.read_csv(pump_data_path, index_col = 0)\n", "df.head(1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### No more copying-pasting" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "image/png": { "height": 358, "width": 511 } }, "output_type": "display_data" } ], "source": [ "# 1. magic for inline plot\n", "# 2. magic to enable retina (high resolution) plots\n", "# https://gist.github.com/minrk/3301035\n", "%matplotlib inline\n", "%config InlineBackend.figure_format = 'retina'\n", "\n", "plt.rcParams['figure.figsize'] = 8, 6\n", "\n", "# create a chart, and we might be tempted to\n", "# paste the code for 'construction_year'\n", "# paste the code for 'gps_height'\n", "plot_data = df['amount_tsh']\n", "sns.kdeplot(plot_data, bw = 1000)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "After making this plot, we might want to do the same for other numeric variables. To do this we can copy the entire cell and modify the parameters. This might be ok in a draft, but after a while the notebook can become quite unmanageable.\n", "\n", "When we realize we're starting to step on our own toes, that we are no longer effective and the development become clumsy, it is time to organize the notebook. Start over, copy the good code, rewrite and generalize bad one.\n", "\n", "Back to our original task of plotting the same graph for other numeric variables, instead of copying and pasting the cell multiple times, we should refactor this a little bit to not repeat ourselves, i.e., create a function to do it instead of copying and pasting. And for the function, write appropriate [docstrings](http://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_numpy.html#example-numpy)." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "def kde_plot(dataframe, variable, upper = None, lower = None, bw = 0.1):\n", " \"\"\" \n", " Plots a density plot for a variable with optional upper and\n", " lower bounds on the data (inclusive)\n", " \n", " Parameters\n", " ----------\n", " dataframe : DataFrame\n", " \n", " variable : str\n", " input column, must exist in the input dataframe.\n", " \n", " upper : int\n", " upper bound for the input column, i.e. data points\n", " exceeding this threshold will be excluded.\n", " \n", " lower : int\n", " lower bound for the input column, i.e. data points\n", " below this threshold will be excluded.\n", " \n", " bw : float, default 0.1\n", " bandwidth for density plot's line.\n", " \n", " References\n", " ----------\n", " Numpy style docstring\n", " - http://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_numpy.html#example-numpy\n", " \"\"\"\n", " plot_data = dataframe[variable]\n", " \n", " if upper is not None:\n", " plot_data = plot_data[plot_data <= upper]\n", " \n", " if lower is not None:\n", " plot_data = plot_data[plot_data >= lower]\n", "\n", " sns.kdeplot(plot_data, bw = bw)\n", " plt.show()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "image/png": { "height": 358, "width": 511 } }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "image/png": { "height": 358, "width": 491 } }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "image/png": { "height": 358, "width": 505 } }, "output_type": "display_data" } ], "source": [ "kde_plot(df, variable = 'amount_tsh', bw = 1000, lower = 0)\n", "kde_plot(df, variable = 'construction_year', bw = 1, lower = 1000, upper = 2016)\n", "kde_plot(df, variable = 'gps_height', bw = 100)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### No more copy-pasting between notebooks \n", "\n", "Have a method that gets used in multiple notebooks? Refactor it into a separate `.py` file so it can live a happy life! Note: In order to import your local modules, you must do three things:\n", "\n", " - put the .py file in a separate folder.\n", " - add an empty `__init__.py` file to the folder so the folder can be recognized as a package.\n", " - add that folder to the Python path with `sys.path.append`." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "# add local python functions\n", "import sys\n", "\n", "# add the 'src' directory as one where we can import modules\n", "src_dir = os.path.join('..', 'src')\n", "sys.path.append(src_dir)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(821, 39)" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# import my method from the source code,\n", "# which drops rows with 0 in them\n", "from features.build_features import remove_invalid_data\n", "\n", "df = remove_invalid_data(pump_data_path)\n", "df.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Jupyter notebook is smart about importing methods. Hence, after importing the method for the first time it will use that version, even if we were to change it afterwards. To overcome this \"issue\" we can use a jupyter notebook extension to tell it to reload the method every time it changes." ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "# Load the \"autoreload\" extension\n", "# it comes with jupyter notebook\n", "%load_ext autoreload\n", "\n", "# always reload all modules\n", "%autoreload 2\n", "\n", "# or we can reload modules marked with \"%aimport\"\n", "# import my method from the source code\n", "\n", "# %autoreload 1\n", "# %aimport features.build_features" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### I'm too good! Now this code is useful to other projects!\n", "\n", "Importing local code is great if you want to use it in multiple notebooks, but once you want to use the code in multiple projects or repositories, it gets complicated. This is when we get serious about isolation!\n", "\n", "We can build a python package to solve that! In fact, there is a [cookiecutter to create Python packages](https://github.com/wdm0006/cookiecutter-pipproject).\n", "\n", "Once we create this package, we can install it in \"editable\" mode, which means that as we change the code the changes will get picked up if the package is used. The process looks like\n", "\n", "```bash\n", "# install cookiecutter first\n", "pip install cookiecutter\n", "\n", "cookiecutter https://github.com/wdm0006/cookiecutter-pipproject\n", "cd package_name\n", "pip install -e .\n", "```\n", " \n", "Now we can have a separate repository for this code and it can be used across projects without having to maintain code in multiple places." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Section 3 Don't let others break your toys" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Include tests.\n", "\n", "### numpy.testing\n", "\n", "Provides useful assertion methods for values that are numerically close and for numpy arrays." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "# the randomly generated data from the normal distribution with a mean of 1\n", "# should have a mean that's almost equal to 0, hence no error occurs\n", "import numpy as np\n", "data = np.random.normal(0.0, 1.0, 1000000)\n", "np.testing.assert_almost_equal(np.mean(data), 0.0, decimal = 2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Also check the docs for [numpy.isclose](http://docs.scipy.org/doc/numpy-dev/reference/generated/numpy.isclose.html) and [numpy.allclose](http://docs.scipy.org/doc/numpy-dev/reference/generated/numpy.allclose.html#numpy.allclose). When making assertions about data, especially where small probabilistic changes or machine precision may result in numbers that aren't **exactly** equal. Consider using this instead of == for numbers involved in anything where randomness may influence the results\n", "\n", "### [engarde](https://github.com/TomAugspurger/engarde) decorators\n", "\n", "A library that lets you practice defensive program -- specifically with pandas `DataFrame` objects. It provides a set of decorators that check the return value of any function that returns a `DataFrame` and confirms that it conforms to the rules." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ab
01.2385630.215904
10.498143-1.178031
2-0.1465210.072514
3-0.1388081.070784
4-0.2185870.654166
\n", "
" ], "text/plain": [ " a b\n", "0 1.238563 0.215904\n", "1 0.498143 -1.178031\n", "2 -0.146521 0.072514\n", "3 -0.138808 1.070784\n", "4 -0.218587 0.654166" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# pip install engarde\n", "import engarde.decorators as ed\n", "\n", "\n", "test_data = pd.DataFrame({'a': np.random.normal(0, 1, 100),\n", " 'b': np.random.normal(0, 1, 100)})\n", "@ed.none_missing()\n", "def process(dataframe):\n", " dataframe.loc[10, 'a'] = 1 # change the 1 to np.nan and the code assertion will break\n", " return dataframe\n", "\n", "process(test_data).head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "`engarde` has an awesome set of decorators:\n", "\n", "- `none_missing` - no NaNs (great for machine learning--sklearn does not care for NaNs)\n", "- `has_dtypes` - make sure the dtypes are what you expect\n", "- `verify` - runs an arbitrary function on the dataframe\n", "- `verify_all` - makes sure every element returns true for a given function\n", "\n", "More can be found [in the docs](http://engarde.readthedocs.org/en/latest/api.html)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Creating a test suite with pytest\n", "\n", "Creating a test suite with [pytest](http://pytest.org/latest/) to start checking the functions we've \n", "written. To pytest `test_` prefixed test functions or methods are test items. For more info, check the [getting started guide](http://docs.pytest.org/en/latest/getting-started.html).\n", "\n", "The term \"[test fixtures](https://en.wikipedia.org/wiki/Test_fixture#Software)\" refers to known objects or mock data used to put other pieces of the system to the the test. We want these to have the same, known state every time.\n", "\n", "For those familiar with [`unittest`](https://github.com/ethen8181/machine-learning/blob/master/python/test.py), this might be data that you read in as part of the `setUp` method. `pytest` does things a bit differently; you define functions that return expected fixtures, and use a special decorator so that your tests automatically get passed the fixture data when you add the fixture function name as an argument.\n", "\n", "We need to set up a way to get some data in here for testing. There are two basic choices — **reading in the actual data or a known subset of it**, or **making up some smaller, fake data**. You can choose whatever you think works best for your project.\n", "\n", "Remove the failing test from above and copy the following into your testing file:" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "import pytest\n", "import pandas as pd\n", "\n", "@pytest.fixture()\n", "def df():\n", " \"\"\"read in the raw data file and return the dataframe\"\"\"\n", " pump_data_path = os.path.join('..', 'data', 'raw', 'pumps_train_values.csv')\n", " df = pd.read_csv(pump_data_path)\n", " return df\n", "\n", "\n", "def test_df_fixture(df):\n", " assert df.shape == (59400, 40)\n", "\n", " useful_columns = ['amount_tsh', 'gps_height', 'longitude', 'latitude', 'region',\n", " 'population', 'construction_year', 'extraction_type_class',\n", " 'management_group', 'quality_group', 'source_type',\n", " 'waterpoint_type', 'status_group']\n", " \n", " for column in useful_columns:\n", " assert column in df.columns" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "When can then run `py.test` from the command line, where the testing code resides.\n", "\n", "\n", "## Other Tips and Tricks\n", "\n", "**Version control:** Use version control such as github! Except for big data file where you might turn to other cloud database, s3, etc. If you are in fact using github, you might also be interested in the [nbdime](http://nbdime.readthedocs.io/en/latest/) (diffing and merging of Jupyter Notebooks) project. It makes checking jupyter notebook changes so much easier.\n", "\n", "**Logging:** Use [logging](http://nbviewer.jupyter.org/github/ethen8181/machine-learning/blob/master/python/logging.ipynb) to record to process instead of printing.\n", "\n", "**Issue tracking:** Keep track of the bugs. A minimal useful bug database should include:\n", "\n", "- The observed behavior. Complete steps to reproduce the bug\n", "- The expected behavior\n", "- Who is it assigned to\n", "- Whether it has been fixed or not\n", "\n", "**Set up a clear workflow:** Establish the workflow before diving into the project. This includes using a unified file structure for the project, e.g. [cookiecutter-data-science](https://github.com/drivendata/cookiecutter-data-science)\n", "\n", "**Use joblib for caching output:**\n", "\n", "You thought your neural network for three days and now you are ready to build on top of it. But you forgot to plug your laptop to a power source and it runs out of batteries. So you scream: Why didn’t I pickle!? The answer is: because it is pain in the back. Managing file names, checking if the file exists, saving, loading ... What to do instead? Use `joblib`.\n", "\n", "```python\n", "from sklearn.externals.joblib import Memory\n", "\n", "memory = Memory(cachedir='/tmp', verbose=0)\n", "\n", "@memory.cache\n", "def computation(p1, p2):\n", " ...\n", "```\n", "\n", "With three lines of code, we get caching of the output of any function. Joblib traces parameters passed to a function, and if the function has been called with the same parameters it returns the return value cached on a disk.\n", "\n", "**Jupyter Notebooks Extension:**\n", "\n", "The [Jupyter notebook extension project](https://github.com/ipython-contrib/jupyter_contrib_nbextensions) contains a collection of extensions that adds functionality to the default jupyter notebook. Some useful ones that I enjoy using includes:\n", "\n", "- Table of content\n", "- Code snippet\n", "- Code folding\n", "- Table beautifier\n", "- Auto equation numbering\n", "- etc.\n", "\n", "Taking some time to configure them will most likely make working with notebooks even more pleasant." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Reference\n", "\n", "- [Blog: 10 tips on using Jupyter Notebook](https://hackernoon.com/10-tips-on-using-jupyter-notebook-abc0ba7028a4)\n", "- [Blog: An Introduction to Semantic Versioning](https://learningd3.com/blog/d3-versioning/)\n", "- [Github: Data Science is Software | SciPy 2016 Tutorial | Peter Bull & Isaac Slavitt](https://github.com/drivendata/data-science-is-software)\n", "- [Youtube: Data Science is Software | SciPy 2016 Tutorial | Peter Bull & Isaac Slavitt](https://www.youtube.com/watch?v=EKUy0TSLg04&index=2&list=PLYx7XA2nY5Gf37zYZMw6OqGFRPjB1jCy6)\n", "- [Youtube: 10 things you really should know about jupyter notebooks - Jakub Czakon](https://www.youtube.com/watch?v=FwUcJFSAfQw)" ] } ], "metadata": { "anaconda-cloud": {}, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.4" }, "notify_time": "30", "toc": { "nav_menu": { "height": "350px", "width": "252px" }, "number_sections": true, "sideBar": true, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": true, "toc_position": {}, "toc_section_display": "block", "toc_window_display": true }, "varInspector": { "cols": { "lenName": 16, "lenType": 16, "lenVar": 40 }, "kernels_config": { "python": { "delete_cmd_postfix": "", "delete_cmd_prefix": "del ", "library": "var_list.py", "varRefreshCmd": "print(var_dic_list())" }, "r": { "delete_cmd_postfix": ") ", "delete_cmd_prefix": "rm(", "library": "var_list.r", "varRefreshCmd": "cat(var_dic_list()) " } }, "types_to_exclude": [ "module", "function", "builtin_function_or_method", "instance", "_Feature" ], "window_display": false } }, "nbformat": 4, "nbformat_minor": 1 }