def most_common_lineup_position(retro):
TABLE_FLAG = False
if isinstance(retro, _Table):
TABLE_FLAG = True
retro = retro.to_df()
# Order of operations:
# 1. Get PA counts
# 2. Turn Lineup_Order into a column
# 3. Rename column to PA
# 4. Sort on PA in descending order
lineup_pos = retro.groupby(['Batter_ID', 'Lineup_Order'])['Inning'].\
count().\
reset_index(level='Lineup_Order').\
rename(columns={'Inning': 'PA'}).\
sort_values('PA', ascending=False)
# Duplicates indicate other positions. By keeping first, we keep the most
# common due to the sorting
most_common = ~lineup_pos.index.duplicated(keep='first')
lineup_pos = lineup_pos.loc[most_common, ['Lineup_Order']].sort_index()
if TABLE_FLAG:
return _Table.from_df(lineup_pos.reset_index())
else:
return lineup_pos
def fast_run_expectancy(retro, re):
TABLE_FLAG = False
if isinstance(retro, _Table):
TABLE_FLAG = True
retro = retro.to_df()
re = re.to_df()
re = re.set_index(['Outs', 'Start_Bases'])
# Build current out-runner states
idx = list(zip(retro['Outs'], retro['Start_Bases']))
# Extract run potentials
retro['Run_Expectancy'] = re.loc[idx].values
next_outs = retro['Outs'] + retro['Event_Outs']
# Build next out-runner states
idx = list(zip(next_outs, retro['End_Bases']))
# Extract run potentials
retro['Run_Expectancy_Next'] = re.loc[idx].values
# When the inning ends, there are 3 outs. That is not in the run
# expectancy matrix so inning ending plate appearances will have an NA
# value here. We fill those with 0.
retro['Run_Expectancy_Next'].fillna(0, inplace=True)
return _Table.from_df(retro) if TABLE_FLAG else retro
def fill_null(table, fill_column=None, fill_value=None, fill_method=None):
TABLE_FLAG = False
if isinstance(table, _Table):
TABLE_FLAG = True
table = table.to_df()
data = table[fill_column] if fill_column is not None else table
data = data.fillna(value=fill_value, method=fill_method)
return _Table.from_df(data) if TABLE_FLAG else data
def get_first_from_group(table, groupby):
TABLE_FLAG = False
if isinstance(table, _Table):
TABLE_FLAG = True
table = table.to_df()
out = table.sort_values(groupby).\
drop_duplicates(subset=groupby, keep='first')
if TABLE_FLAG:
return _Table.from_df(out)
else:
return out
def merge(t1, t2, on, how='outer', fillna=True):
DS_FLAG = False
if isinstance(t1, _Table):
t1 = t1.to_df()
DS_FLAG = True
if isinstance(t2, _Table):
t2 = t2.to_df()
full_t = _pd.merge(t1, t2, how=how, left_on=on, right_on=on)
if fillna:
full_t.fillna(0, inplace=True)
if DS_FLAG:
return _Table.from_df(full_t)
else:
return full_t
def merge(t1, t2, on, how='outer', fillna=True):
import pandas as pd
from datascience import Table
DS_FLAG = False
if isinstance(t1, Table):
t1 = t1.to_df()
DS_FLAG = True
if isinstance(t2, Table):
t2 = t2.to_df()
full_t = pd.merge(t1, t2, how=how, left_on=on, right_on=on)
if fillna:
full_t.fillna(0, inplace=True)
if DS_FLAG:
return Table.from_df(full_t)
else:
return full_t
def multi_sort(table, by, descending=True, na_position='first'):
sorted_df = table.to_df().sort_values(by,
ascending=not descending,
na_position=na_position)
return _Table.from_df(sorted_df)
def concat(table_list):
df = _pd.concat([t.to_df() for t in table_list])
return _Table.from_df(df)
def fill_null(table, value=None, method=None):
df = table.to_df().fillna(value=value, method=method)
return _Table.from_df(df)
#Hence is of little use for prediction of shelf life. hence droping those columns also from further analysis
print(
"Also Residual Oxygen, Moisture (%) and Hexanal (ppm) are charecteristics of aged samples. Hence is of little use for prediction of shelf life. hence droping those columns also from further analysis"
)
ProductTable = ProductTable.drop('Moisture (%)')
ProductTable = ProductTable.drop('Residual Oxygen (%)')
ProductTable = ProductTable.drop('Hexanal (ppm)')
#Also drop colomn Study Number/Sample ID as this is not affecting shelf life in anyway
'''ProductTable=ProductTable.drop('Study Number')
ProductTable=ProductTable.drop('Sample ID')'''
#Drop Duplicate Entries iF there are any
pandasDF = ProductTable.to_df()
pandasDF.drop_duplicates(keep='first',
inplace=True) #inplace=True modify original record
ProductTable = Table.from_df(pandasDF)
'''ProductTable=ProductTable.move_column('Difference From Fresh',0)
ProductTable=ProductTable.move_column('Sample Age (Weeks)',1)
ProductTable=ProductTable.move_column('Processing Agent Stability Index',2)
ProductTable=ProductTable.move_column('Process Type',3)'''
#--------------------------------------------------------------------------------------------------------------------
#ONE HOT ENCODING(Custom)
#--------------------------------------------------------------------------------------------------------------------
ProductTable.append_column('ProcessTypeC', False)
ProductTable.append_column('ProcessTypeB', False)
ProductTable.append_column('ProcessTypeA', False)
ProductTable['ProcessTypeA'] = ProductTable.apply(
lambda x: True if x == 'A' else False, 'Process Type')
ProductTable['ProcessTypeC'] = ProductTable.apply(
lambda x: True if x == 'C' else False, 'Process Type')
def from_df(self, df):
# a pandas df
table = Table.from_df(df)
df_name = find_name()
return self.create_with_table_wrap(table, df_name)
