def __init__(self, path):
self.path = path
self.df_fin_all = pd.read_csv(self.path)
# Preprocess data
# Clean the data
dc = data_cleaning()
# remove data with missing ticker symbols
self.df_fin_all = dc.remove_missing_tic_data(self.df_fin_all)
# remove pre IPO data
IPO_path = "D:\\FA\\data\\stock_stats\\IPO_year.csv"
self.df_fin_all = dc.remove_pre_IPO_data(IPO_path, self.df_fin_all)
# Remove rows with missing year information.
self.df_fin_all = dc.remove_missing_year_data(self.df_fin_all)
self.df_fin_all = self.df_fin_all.set_index('fyear')
self.df_fin_all = self.df_fin_all.fillna(0.)
# Select financial statements variables
# Balance Sheet
# Assets
assets_current = ['che', 'rect', 'invt', 'aco', 'act']
assets_rest = ['ppent', 'ivaeq', 'ivao', 'intan', 'ao', 'at']
# Liabilities
liabilities_current = ['dlc', 'ap', 'txp', 'lco', 'lct']
liabilities_rest = [
'dltt', 'txditc', 'lo', 'lt', 'mib', 'pstk', 'ceq', 'seq'
]
self.b_sheet = assets_current + assets_rest + liabilities_current + \
liabilities_rest
# Income Statement
revenue = ['revt']
costs = ['cogs', 'xsga']
operations = ['oibdp', 'oiadp', 'xint', 'nopi']
income = ['spi', 'pi', 'txt', 'ib', 'niadj', 'epspx', 'epsfx']
self.i_sheet = revenue + costs + operations + income
# Cash Flow Statement
cash_oper = [
'ibc', 'xidoc', 'dpc', 'txdc', 'esub', 'sppiv', 'fopo', 'recch',
'invch', 'apalch', 'txach', 'aoloch', 'oancf'
]
cash_investment = [
'ivch', 'siv', 'ivstch', 'capx', 'sppe', 'aqc', 'ivaco', 'ivncf'
]
cash_finance = [
'sstk', 'txbcof', 'prstkc', 'dv', 'dltis', 'dltr', 'dlcch', 'fiao',
'fincf'
]
self.c_sheet = cash_oper + cash_investment + cash_finance
def __init__(self, path):
self.path = path
self.df_fin_all = pd.read_csv(self.path)
# Preprocess data
# Clean the data
dc = data_cleaning()
# remove data with missing ticker symbols
self.df_fin_all = dc.remove_missing_tic_data(self.df_fin_all)
# remove pre IPO data
IPO_path = "/Users/liqiran/Desktop/ml_fa/data/stock_stats/IPO_year.csv"
self.df_fin_all = dc.remove_pre_IPO_data(IPO_path, self.df_fin_all)
# Remove rows with missing year information.
self.df_fin_all = dc.remove_missing_year_data(self.df_fin_all)
self.df_fin_all = self.df_fin_all.set_index('fyear')
self.df_fin_all = self.df_fin_all.fillna(0.)
# Select financial statements variables
self.others = [
're', 'wcapch', 'wcapc', 'unwcc', 'nim', 'citotal', 'cga', 'mrc1',
'mrc2', 'mrc3', 'mrc4', 'mrc5'
]
def __init__(self, path):
self.path = path
self.df_fin_all = pd.read_csv(self.path)
# Preprocess data
# Clean the data
dc = data_cleaning()
# remove data with missing ticker symbols
self.df_fin_all = dc.remove_missing_tic_data(self.df_fin_all)
# remove pre IPO data
IPO_path = "/Users/liqiran/Desktop/ml_fa/data/stock_stats/IPO_year.csv"
self.df_fin_all = dc.remove_pre_IPO_data(IPO_path, self.df_fin_all)
# Remove rows with missing year information.
self.df_fin_all = dc.remove_missing_year_data(self.df_fin_all)
self.df_fin_all = self.df_fin_all.set_index('fyear')
# Select market data for the stock
self.market_data = ['csho', 'mkvalt', 'prcc_c', 'prcc_f']
def __init__(self, path):
self.path = path
self.df_fin_all = pd.read_csv(self.path)
# Preprocess data
# Clean the data
dc = data_cleaning()
# remove data with missing ticker symbols
self.df_fin_all = dc.remove_missing_tic_data(self.df_fin_all)
# remove pre IPO data
#IPO_path = "D:\\FA\\data\\stock_stats\\IPO_year.csv"
IPO_path = os.path.join('..', 'data', 'stock_stats', 'IPO_year.csv')
self.df_fin_all = dc.remove_pre_IPO_data(IPO_path, self.df_fin_all)
# Remove rows with missing year information.
self.df_fin_all = dc.remove_missing_year_data(self.df_fin_all)
self.df_fin_all = self.df_fin_all.set_index('fyear')
# Select market data for the stock
self.market_data = ['csho', 'mkvalt', 'prcc_c', 'prcc_f']