Add StockReader object for grabbing data from websites.

.gitignore

@@ -0,0 +1,4 @@
+.ipynb_checkpoints
+*.png
+*/__pycache__/
+*.egg-info

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 Stefanie Molin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,20 @@
+# Stock Analysis
+Package for making elements of technical analysis of a stock easier. This package is meant to be a starting point for you to develop your own. As such, all the instructions for installing/setup will be assuming you will continue to develop on your end.
+
+## Setup
+### with pip
+```
+# should install requirements.txt packages
+pip install -e stock_analysis # path to top level where setup.py is
+
+# if not, install them explicitly
+pip install -r requirements.txt
+```
+
+### with setup.py
+```
+python setup.py develop
+```
+
+## Usage
+Coming soon, this is a WIP.

requirements.txt

@@ -0,0 +1,2 @@
+pandas==0.23.4
+pandas-datareader==0.7.0

setup.py

@@ -0,0 +1,16 @@
+from distutils.core import setup
+
+setup(
+    name='stock_analysis',
+    version='0.0',
+    description='Classes for technical analysis of stocks.',
+    author='Stefanie Molin',
+    author_email='24376333+stefmolin@users.noreply.github.com',
+    license='MIT',
+    url='https://github.com/stefmolin/stock-analysis',
+    packages=['stock_analysis'],
+    install_requires=[
+          'pandas>=0.23.4',
+          'pandas-datareader==0.7.0'
+    ],
+)

stock_analysis/__init__.py

@@ -0,0 +1,3 @@
+"""Classes for making technical stock analysis easier."""
+
+from .stock_reader import StockReader

stock_analysis/stock_reader.py

@@ -0,0 +1,74 @@
+"""Gathering select stock data."""
+
+import datetime
+import re
+
+import pandas as pd
+import pandas_datareader.data as web
+
+from .utils import label_sanitizer
+
+class StockReader:
+    """Class for reading financial data from websites."""
+
+    def __init__(self, start, end=None):
+        """
+        Create a StockReader object for reading across a given date range.
+
+        Parameters:
+            - start: The first date to include, as a datetime object or
+                     a string in the format 'YYYYMMDD'.
+            - end: The last date to include, as a datetime object or
+                   a string in the format 'YYYYMMDD'. Defaults to today
+                   if not provided.
+
+        Returns:
+            A StockReader object.
+        """
+        self.start, self.end = map(
+            lambda x: x.strftime('%Y%m%d') if isinstance(x, datetime.date) \
+            else re.sub(r'\D', '', x),
+            [start, end or datetime.date.today()]
+        )
+
+    @label_sanitizer
+    def get_ticker_data(self, ticker):
+        """
+        Get historical OHLC data from Investors Exchange (IEX)
+        for given date range and ticker.
+
+        Parameter:
+            - ticker: The stock symbol to lookup as a string.
+
+        Returns:
+            A pandas dataframe with the stock data.
+        """
+        return web.DataReader(ticker, 'iex', self.start, self.end)
+
+    @label_sanitizer
+    def get_bitcoin_data(self):
+        """
+        Get bitcoin historical OHLC data from coinmarketcap.com for given date range.
+
+        Returns:
+            A pandas dataframe with the bitcoin data.
+        """
+        return pd.read_html(
+            'https://coinmarketcap.com/currencies/bitcoin/historical-data/?'
+            'start={}&end={}'.format(
+                self.start, self.end
+            ),
+            parse_dates=True,
+            index_col='Date'
+        )[0]
+
+    @label_sanitizer
+    def get_sp500_data(self):
+        """
+        Get historical OHLC data from Yahoo Finance for the S&P 500 Index
+        for given date range.
+
+        Returns:
+            A pandas dataframe with the S&P 500 index data.
+        """
+        return web.get_data_yahoo('^GSPC', self.start, self.end)

stock_analysis/utils.py

@@ -0,0 +1,50 @@
+"""Utility functions for stock analysis."""
+
+from functools import wraps
+import re
+
+def _sanitize_label(label):
+    """
+    Clean up a label by removing non-letter, non-space characters and
+    putting in all lowercase with underscores replacing spaces.
+
+    Parameters:
+        - label: The text you want to fix.
+
+    Returns:
+        The sanitized label.
+    """
+    return re.sub(r'[^\w\s]', '', label).lower().replace(' ', '_')
+
+def label_sanitizer(method, *args, **kwargs):
+    """
+    Decorator around a method that returns a dataframe to
+    clean up all labels in said dataframe (column names and index name)
+    by removing non-letter, non-space characters and
+    putting in all lowercase with underscores replacing spaces.
+
+    Parameters:
+        - method: The dataframe with labels you want to fix.
+        - args: Additional positional arguments to pass to the wrapped method.
+        - kwargs: Additional keyword arguments to pass to the wrapped method.
+
+    Returns:
+        A decorated method.
+    """
+    # keep the docstring of the data method for help()
+    @wraps(method)
+    def method_wrapper(self, *args, **kwargs):
+        df = method(self, *args, **kwargs)
+
+        # fix the column names
+        df.columns = [
+            _sanitize_label(col) for col in df.columns
+        ]
+
+        # fix the index name
+        df.index.rename(
+            _sanitize_label(df.index.name),
+            inplace=True
+        )
+        return df
+    return method_wrapper