def setUpClass(cls):
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
left_fileName = 'test_join_left_table.csv'
right_fileName = 'test_join_right_table.csv'
data_left = os.path.join(DATA_DIR, left_fileName)
data_left = data_left.replace('\\', '/')
data_right = os.path.join(DATA_DIR, right_fileName)
data_right = data_right.replace('\\', '/')
dfsDatabase = "dfs://testjoinDB"
# connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
_create_odf_csv(data_left, data_right)
# import
Csv.odf_csv_left = orca.read_csv(data_left,
dtype={"TRDSTAT": "SYMBOL"})
Csv.odfs_csv_left = orca.read_table(dfsDatabase, 'tb_left')
Csv.pdf_csv_left = pd.read_csv(data_left, parse_dates=[1])
Csv.odf_csv_right = orca.read_csv(data_right,
dtype={"TRDSTAT": "SYMBOL"})
Csv.odfs_csv_right = orca.read_table(dfsDatabase, 'tb_right')
Csv.pdf_csv_right = pd.read_csv(data_right, parse_dates=[0])
def setUpClass(cls):
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
fileName = 'USPricesSample.csv'
data = os.path.join(DATA_DIR, fileName)
data = data.replace('\\', '/')
# Orca connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
# odf from import
Csv.odf_csv = orca.read_csv(data,
dtype={
"PERMNO": np.int32,
"date": 'DATE',
"TRDSTAT": 'SYMBOL',
"DLSTCD": np.float32,
"DLPRC": np.float32,
"VOL": np.float32,
"SHROUT": np.float32
})
# pdf from import
Csv.pdf_csv = pd.read_csv(data,
parse_dates=[1],
dtype={
"PERMNO": np.int32,
"SHRCD": np.int32,
"HEXCD": np.int32,
"DLSTCD": np.float32,
"DLPRC": np.float32,
"VOL": np.float32,
"SHROUT": np.float32
})
def setUpClass(cls):
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
fileName = 'onlyNumericalColumns.csv'
data = os.path.join(DATA_DIR, fileName)
data = data.replace('\\', '/')
# Orca connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
Csv.pdf_csv = pd.read_csv(data)
Csv.odf_csv = orca.read_csv(data)
def setUpClass(cls):
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
left_fileName = 'test_merge_left_table.csv'
right_fileName = 'test_merge_right_table.csv'
datal = os.path.join(DATA_DIR, left_fileName)
datal= datal.replace('\\', '/')
datar = os.path.join(DATA_DIR, right_fileName)
datar = datar.replace('\\', '/')
dfsDatabase = "dfs://testMergeDB"
# connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
_create_odf_csv(datal, datar)
# import
Csv.odf_csv_left = orca.read_csv(datal)
Csv.odfs_csv_left = orca.read_table(dfsDatabase, 'tickers')
Csv.pdf_csv_left = pd.read_csv(datal, parse_dates=[0,1])
Csv.odf_csv_right = orca.read_csv(datar)
Csv.odfs_csv_right = orca.read_table(dfsDatabase, 'values')
Csv.pdf_csv_right = pd.read_csv(datar)
def setUpClass(cls):
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
fileName = 'USPricesSample.csv'
data = os.path.join(DATA_DIR, fileName)
data = data.replace('\\', '/')
# Orca connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
# import
Csv.odf_csv = orca.read_csv(data)
Csv.odf_csv.set_index('date', inplace=True)
Csv.pdf_csv = pd.read_csv(data)
Csv.pdf_csv.set_index('date', inplace=True)
def setUpClass(cls):
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
fileName = 'USPricesSample.csv'
data = os.path.join(DATA_DIR, fileName)
data = data.replace('\\', '/')
# connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
Csv.odf_csv = orca.read_csv(data,
dtype={
"DLSTCD": np.float32,
"DLPRC": np.float32
})
# pdf from import
Csv.pdf_csv = pd.read_csv(data)
Csv.odf_csv = Csv.odf_csv.drop(columns=['DLRET'])
Csv.pdf_csv.drop(columns=['DLRET'], inplace=True)
def main():
df = orca.read_csv(US)
price_data = load_price_data(df)
tradables = gen_trade_tables(price_data)
start_date, end_date = orca.Timestamp("1996.01.01"), orca.Timestamp(
"2017.01.01")
holding_days = 5
groups = 10
ports = form_portfolio(start_date, end_date, tradables, holding_days,
groups, 2)
daily_rtn = price_data.loc[price_data.date.between(start_date, end_date),
['date', 'PERMNO', 'RET']]
last_days = price_data.groupby('PERMNO')['date'].max()
last_days.rename("last_day", inplace=True)
stock_pnl = calc_stock_pnl(ports, daily_rtn, holding_days, end_date,
last_days)
port_pnl = stock_pnl.groupby('date')['pnl'].sum()
cumulative_return = port_pnl.cumsum()
cumulative_return.plot()
plt.show()
from setup.settings import *
import csv
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
PRECISION_POINT = 1
fileName = 'USPrices.csv'
data = os.path.join(DATA_DIR, fileName)
data = data.replace('\\', '/')
# Orca connect to a DolphinDB server
orca.connect(HOST, PORT, "admin", "123456")
# import
startTime = time.time()
odf = orca.read_csv(data)
print("Orca spent " + str(time.time() - startTime) + "s importing '" +
fileName + "'")
# generate report.csv
csvfile = open(WORK_DIR + 'report.csv', 'a')
writer = csv.writer(csvfile)
writer.writerow(
[time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))])
writer.writerow(['groupby', 'orca'])
def reportToCsv(operation, timecost):
lines = [operation, timecost]
writer.writerow(lines)
import orca
from setup.settings import *
import matplotlib.pyplot as plt
import os.path as path
# configure data directory
DATA_DIR = path.abspath(path.join(__file__, "../setup/data"))
fileName = 'wages_hours.csv'
data = path.join(DATA_DIR, fileName)
data = data.replace('\\', '/')
orca.connect(HOST, PORT, "admin", "123456")
odf = orca.read_csv(data)
odf.head()
odf = orca.read_csv(data, sep="\t")
odf.head()
odf2 = odf[["AGE", "RATE"]]
odf2.head()
data_sorted = odf2.sort_values(["AGE"])
data_sorted.head()
data_sorted.set_index("AGE", inplace=True)
data_sorted.head()
data_sorted.plot()
plt.show()
def a_load(self):
self.df_ticker = orca.read_csv(self.ticker_file)
self.df_ticker.columns = ticker_columns
self.df_value = orca.read_csv(self.value_file)
self.df_value.columns = value_columns