mberrien-fitzsimons

dist: xenial
language: python
python:
  - "3.7.1"
install:
  - pip install -r requirements.txt
  - pip install pandas
script:
  - pytest

mberrien-fitzsimons

from setuptools import setup

install_requires = [
    'pandas>=0.25.0',
    'numpy>=1.15.4',
    'functools']

setup(name='misha_math',
      version='0.0.1',
      description='test',

mberrien-fitzsimons

import pytest

from mypackage_two.pandas_math import create_empty_dataframe

class TestCreateEmptyDataframe(object):

    def test_on_create_empty_dataframe(self):

        actual = len(create_empty_dataframe(['foo', 'bar'], 20))
        expected = 20

mberrien-fitzsimons

import pandas as pd
import numpy as np

def create_empty_dataframe(new_column_list, num_rows):

       """
       Creates a new dataframe filled with zeroes from a specified
       list and number of rows.
        Args:
            new_col_list (object): List of column names.

mberrien-fitzsimons

import pandas as pd
import numpy as np

def create_empty_dataframe(new_column_list, num_rows):
    
       """
       Creates a new dataframe filled with zeroes from a specified 
       list and number of rows. 

        Args:

mberrien-fitzsimons

# put data processing code into function
def process_alphavantage_data_create_dow_dummies(raw_data_file):
    raw_data_file['timestamp'] = pd.to_datetime(raw_data_file['timestamp'])
    raw_data_file['day_of_week'] = raw_data_file['timestamp'].dt.day_name()
    dummies = pd.get_dummies(raw_data_file['day_of_week'])
    raw_data_file.drop(columns=['day_of_week'], inplace=True)
    raw_data_file = pd.concat([raw_data_file, dummies], axis=1)
    # we are only interested in running a regression of volume against the dummy 
    # variables for days of the week. Because of this we will drop the remaining 
    # variables before importing it to our processed data folder

mberrien-fitzsimons

# Put data collection code into a .py document in the src/d00_utils folder. From there 
# it can be imported into different jupyter notebooks for easy data 
def alphavantage_api_csv_download_raw(function, symbol, alpha_vantage_key):
    function = function
    symbol = symbol
    datatype = 'csv'
    url = f"https://www.alphavantage.co/query?function={function}&symbol={symbol}\
          &datatype={datatype}&apikey={ALPHA_VANTAGE_KEY}"
    return pd.read_csv(url)

mberrien-fitzsimons

# save the model
filename = '../data/04_models/finalized_model.sav'
pickle.dump(model, open(filename, 'wb'))

mberrien-fitzsimons

# import required library 
from statsmodels.formula.api import ols

#Define the Problem
outcome = 'volume'
x_cols = ['Friday', 'Monday', 'Thursday', 'Tuesday', 'Wednesday']

#Fitting the actual model
predictors = '+'.join(x_cols)
formula = outcome + "~" + predictors

mberrien-fitzsimons

# read new dataframe in from processed data folder
msft_model_df = pd.read_csv('../data/03_processed/msft_proc.csv')