Merge pull request #14 from cooperdff/features

Features

.tox/log/GLOB-0.log

@@ -0,0 +1,40 @@
+action: GLOB, msg: packaging
+cwd: C:\Users\JCoop\Documents\GitHub\nflfastPy
+cmd: 'c:\users\jcoop\anaconda3\envs\myenv\python.exe' setup.py sdist --formats=zip --dist-dir '.tox\dist'
+running sdist
+running egg_info
+writing nfl_data_py.egg-info\PKG-INFO
+writing dependency_links to nfl_data_py.egg-info\dependency_links.txt
+writing requirements to nfl_data_py.egg-info\requires.txt
+writing top-level names to nfl_data_py.egg-info\top_level.txt
+reading manifest file 'nfl_data_py.egg-info\SOURCES.txt'
+writing manifest file 'nfl_data_py.egg-info\SOURCES.txt'
+running check
+creating nfl_data_py-0.1.5
+creating nfl_data_py-0.1.5\nfl_data_py
+creating nfl_data_py-0.1.5\nfl_data_py.egg-info
+copying files to nfl_data_py-0.1.5...
+copying README.md -> nfl_data_py-0.1.5
+copying setup.py -> nfl_data_py-0.1.5
+copying nfl_data_py\__init__.py -> nfl_data_py-0.1.5\nfl_data_py
+copying nfl_data_py.egg-info\PKG-INFO -> nfl_data_py-0.1.5\nfl_data_py.egg-info
+copying nfl_data_py.egg-info\SOURCES.txt -> nfl_data_py-0.1.5\nfl_data_py.egg-info
+copying nfl_data_py.egg-info\dependency_links.txt -> nfl_data_py-0.1.5\nfl_data_py.egg-info
+copying nfl_data_py.egg-info\requires.txt -> nfl_data_py-0.1.5\nfl_data_py.egg-info
+copying nfl_data_py.egg-info\top_level.txt -> nfl_data_py-0.1.5\nfl_data_py.egg-info
+Writing nfl_data_py-0.1.5\setup.cfg
+creating '.tox\dist\nfl_data_py-0.1.5.zip' and adding 'nfl_data_py-0.1.5' to it
+adding 'nfl_data_py-0.1.5'
+adding 'nfl_data_py-0.1.5\nfl_data_py'
+adding 'nfl_data_py-0.1.5\nfl_data_py.egg-info'
+adding 'nfl_data_py-0.1.5\PKG-INFO'
+adding 'nfl_data_py-0.1.5\README.md'
+adding 'nfl_data_py-0.1.5\setup.cfg'
+adding 'nfl_data_py-0.1.5\setup.py'
+adding 'nfl_data_py-0.1.5\nfl_data_py\__init__.py'
+adding 'nfl_data_py-0.1.5\nfl_data_py.egg-info\dependency_links.txt'
+adding 'nfl_data_py-0.1.5\nfl_data_py.egg-info\PKG-INFO'
+adding 'nfl_data_py-0.1.5\nfl_data_py.egg-info\requires.txt'
+adding 'nfl_data_py-0.1.5\nfl_data_py.egg-info\SOURCES.txt'
+adding 'nfl_data_py-0.1.5\nfl_data_py.egg-info\top_level.txt'
+removing 'nfl_data_py-0.1.5' (and everything under it)

nfl_data_py/__init__.py

@@ -36,9 +36,9 @@ def import_pbp_data(years, columns=None, downcast=True):
 
         try:
             if len(columns) != 0:
-                data = pandas.read_parquet(url1 + str(year) + url2, columns=columns, engine='fastparquet')
+                data = pandas.read_parquet(url1 + str(year) + url2, columns=columns, engine='auto')
             else:
-                data = pandas.read_parquet(url1 + str(year) + url2, engine='fastparquet')
+                data = pandas.read_parquet(url1 + str(year) + url2, engine='auto')
 
             raw = pandas.DataFrame(data)
             raw['season'] = year
@@ -84,7 +84,8 @@ def import_weekly_data(years, columns=None, downcast=True):
         columns = []
 
     # read weekly data
-    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/player_stats.parquet', engine='fastparquet')
+    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/player_stats.parquet', engine='auto')
+
     data = data[data['season'].isin(years)]
 
     if len(columns) > 0:
@@ -120,7 +121,7 @@ def import_seasonal_data(years, s_type='REG'):
         raise ValueError('Only REG, ALL, POST allowed for s_type.')
 
     # import weekly data
-    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/player_stats.parquet', engine='fastparquet')
+    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/player_stats.parquet', engine='auto')
 
     # filter to appropriate season_type
     if s_type == 'ALL':
@@ -179,7 +180,8 @@ def see_pbp_cols():
     """
 
     # load pbp file, identify columns
-    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/play_by_play_2020.parquet', engine='fastparquet')
+    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/play_by_play_2020.parquet', engine='auto')
+
     cols = data.columns
 
     return cols
@@ -193,7 +195,8 @@ def see_weekly_cols():
     """
 
     # load weekly file, identify columns
-    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/player_stats.parquet', engine='fastparquet')
+    data = pandas.read_parquet(r'https://github.com/nflverse/nflfastR-data/raw/master/data/player_stats.parquet', engine='auto')
+
     cols = data.columns
 
     return cols
@@ -284,14 +287,8 @@ def import_schedules(years):
     scheds = pandas.DataFrame()
 
     # import schedule for specified years
-    for x in years:
-
-        try:
-            temp = pandas.read_csv(r'https://raw.githubusercontent.com/cooperdff/nfl_data_py/main/data/schedules//' + str(x) + '.csv').drop('Unnamed: 0', axis=1)
-            scheds = scheds.append(temp)
-
-        except:
-            print('Data not available for ' + str(x))
+    scheds = pandas.read_csv(r'http://www.habitatring.com/games.csv')    
+    scheds = scheds[scheds['season'].isin(years)]
 
     return scheds
 
@@ -513,6 +510,58 @@ def import_ids(columns=None, ids=None):
     return df
 
 
+def import_ids(columns=None, ids=None):
+    """Import mapping table of ids for most major data providers
+    
+    Args:
+        columns (List[str]): list of columns to return
+        ids (List[str]): list of specific ids to return
+        
+    Returns:
+        DataFrame
+    """
+
+    # create list of id options
+    avail_ids = ['mfl_id', 'sportradar_id', 'fantasypros_id', 'gsis_id', 'pff_id',
+       'sleeper_id', 'nfl_id', 'espn_id', 'yahoo_id', 'fleaflicker_id',
+       'cbs_id', 'rotowire_id', 'rotoworld_id', 'ktc_id', 'pfr_id',
+       'cfbref_id', 'stats_id', 'stats_global_id', 'fantasy_data_id']
+    avail_sites = [x[:-3] for x in avail_ids]
+
+    # check variable types
+    if columns is None:
+        columns = []
+
+    if ids is None:
+        ids = []
+
+    if not isinstance(columns, list):
+        raise ValueError('columns variable must be list.')
+
+    if not isinstance(ids, list):
+        raise ValueError('ids variable must be list.')
+
+    # confirm id is in table
+    if False in [x in avail_sites for x in ids]:
+        raise ValueError('ids variable can only contain ' + ', '.join(avail_sites))
+
+    # import data
+    df = pandas.read_csv(r'https://raw.githubusercontent.com/dynastyprocess/data/master/files/db_playerids.csv')
+
+    rem_cols = [x for x in df.columns if x not in avail_ids]
+    tgt_ids = [x + '_id' for x in ids]
+
+    # filter df to just specified columns
+    if len(columns) > 0 and len(ids) > 0:
+        df = df[set(tgt_ids + columns)]
+    elif len(columns) > 0 and len(ids) == 0:
+        df = df[set(avail_ids + columns)]
+    elif len(columns) == 0 and len(ids) > 0:
+        df = df[set(tgt_ids + rem_cols)]
+
+    return df
+
+
 def clean_nfl_data(df):
     """Cleans descriptive data for players and teams to help with consistency across datasets
     
@@ -592,6 +641,13 @@ def clean_nfl_data(df):
         'SFO': 'SF',
         'TAM': 'TB'
     }
+
+    na_replace = {
+        'NA':np.nan
+    }
+
+    for col in df.columns:
+        df.replace({col:na_replace}, inplace=True)
 
     if 'name' in df.columns:
         df.replace({'name': name_repl}, inplace=True)

nfl_data_py/tests/nfl_test.py

@@ -0,0 +1,75 @@
+from unittest import TestCase
+import pandas as pd
+
+import nfl_data_py as nfl
+
+class test_pbp(TestCase):
+    def test_is_df(self):
+        s = nfl.import_pbp_data([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_weekly(TestCase):
+    def test_is_df(self):
+        s = nfl.import_weekly_data([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_seasonal(TestCase):
+    def test_is_df(self):
+        s = nfl.import_seasonal_data([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_pbp_cols(TestCase):
+    def test_is_list(self):
+        s = nfl.see_pbp_cols()
+        self.assertEqual(True, isinstance(set(nfl.see_pbp_cols()), set))
+
+class test_weekly_cols(TestCase):
+    def test_is_list(self):
+        s = nfl.see_weekly_cols()
+        self.assertEqual(True, isinstance(set(nfl.see_pbp_cols()), set))
+
+class test_rosters(TestCase):
+    def test_is_df(self):
+        s = nfl.import_rosters([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_team_desc(TestCase):
+    def test_is_df(self):
+        s = nfl.import_team_desc()
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_schedules(TestCase):
+    def test_is_df(self):
+        s = nfl.import_schedules([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_wins(TestCase):
+    def test_is_df(self):
+        s = nfl.import_win_totals([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_officials(TestCase):
+    def test_is_df(self):
+        s = nfl.import_officials([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_draft_picks(TestCase):
+    def test_is_df(self):
+        s = nfl.import_draft_picks([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))		
+
+class test_draft_values(TestCase):
+    def test_is_df(self):
+        s = nfl.import_draft_values()
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_combine(TestCase):
+    def test_is_df(self):
+        s = nfl.import_combine_data([2020])
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+
+class test_ids(TestCase):
+    def test_is_df(self):
+        s = nfl.import_ids()
+        self.assertEqual(True, isinstance(s, pd.DataFrame))
+

setup.py

@@ -18,7 +18,8 @@
 EMAIL = '[email protected]'
 AUTHOR = 'cooperdff'
 REQUIRES_PYTHON = '>=3.6.0'
-VERSION = '0.1.5'
+VERSION = '0.1.6'
+
 
 # What packages are required for this module to be executed?
 REQUIRED = [
@@ -107,12 +108,9 @@ def run(self):
     python_requires=REQUIRES_PYTHON,
     url=URL,
     packages=find_packages(exclude=["tests", "*.tests", "*.tests.*", "tests.*"]),
-    # If your package is a single module, use this instead of 'packages':
-    # py_modules=['mypackage'],
+    test_suite='nose.collector',
+    tests_require=['nose'],
 
-    # entry_points={
-    #     'console_scripts': ['mycli=mymodule:cli'],
-    # },
     install_requires=REQUIRED,
     extras_require=EXTRAS,
     include_package_data=True,

tox.ini

@@ -0,0 +1,8 @@
+# content of: tox.ini , put in same dir as setup.py
+[tox]
+envlist = python2.7,python3.5,python3.6,python3.7,python3.8,python3.9
+[testenv]
+deps = pytest
+# run the tests
+# ... or run any other command line tool you need to run here
+commands = pytest