Please help with this code, since I am unable to make this code work "OLS Regression[3]" from RDP wi

leogabriel.banas01

The chart table is not returning any values for OLS regression. Full code below and I have highlighted in bold for the code on "OLS Regression[3]".

 

import getpass

import refinitiv.dataplatform as rdp  # the RDP library for Python

import pandas as pd

import numpy as np  

import cufflinks as cf  # to plot graph by pandas data frame
 
APP_KEY = getpass.getpass("Enter the app key: ")
 
rdp.open_desktop_session(APP_KEY)
 
RICs = ["USCPI=ECI","JPCPI=ECI","PHCPI=ECI"] # the list of RICs

s_date = "2018-01-02" # start date

e_date = "2018-12-30" # end date

#TBD - remove later pd.set_option('display.max_columns', None)

lastPriceField = "VALUE" # the last price field of these RICs

data = pd.DataFrame() # define data is a DataFrame

for aRIC in RICs: # request daily last price for each RIC

    df= rdp.get_historical_price_summaries(aRIC,start=s_date,end=e_date,interval = rdp.Intervals.MONTHLY,fields=[lastPriceField])

    if df is None: # check if there is any error

        print("Error for RIC " + aRIC + ":" + str(rdp.get_last_status()['error'])) # print the error

    else:

        df[lastPriceField] = df[lastPriceField].astype(float) # convert string type to float

        data[aRIC] = df[lastPriceField] # create the RIC's last price column

data # display daily last price of the RICs

data.dropna(inplace=True)  # deletes rows with NaN values

data.index.names = ['DATE'] # set index name to be 'DATE'

data.sort_values(by=['DATE'], inplace=True, ascending=True) # sort prices according to the 'DATE' column in ascending order

data #display sorted prices

logReturns = np.log(data / data.shift(1)) # calculate the Log Returns
 
logReturns # display the result

cf.set_config_file(offline=True)

logReturns.iplot(kind='line', subplots=True)

data.corr() # calculate the Correlation Matrix.

data.corr().iplot(kind='line')
 
#No chart is returning
def add_lags(data, ric, lags):
    cols = []
    df = pd.DataFrame(data[ric]) #create data frame of the RIC
    for lag in range(1, lags + 1):
        col = 'lag_{}'.format(lag)  # defines the column name
        df[col] = df[ric].shift(lag)  # creates the lagged data column
        cols.append(col)  # stores the column name
        df.dropna(inplace=True)  # gets rid of incomplete data rows
        return df, cols
    dfs = {}
    for ric in RICs:
        df, cols = add_lags(data, ric, 5) # create the lagged data of a RIC
        dfs[ric] = df # create the RIC's logged data column 
        print(dfs[ric]) # print the lagged data of the RIC
        regs = {}
    for ric in RICs:
        df = dfs[ric]  # getting logged data of the RIC
        reg = np.linalg.lstsq(df[cols], df[ric], rcond=-1)[0]  # the OLS regression
        regs[ric] = reg  # storing the results
        print('{:10} | {}'.format(ric, regs[ric])) # print the results
    for ric in RICs:
        res = pd.DataFrame(dfs[ric][ric])  # pick the data frame of the original time series
        res['PRED'] = np.dot(dfs[ric][cols], regs[ric])  # creates the "prediction" values
        layout1 = cf.Layout(height=450,width=1000)# Define a Layout with desired height and width
        res.iloc[-50:].iplot(layout=layout1) # plot the graph

 

Thanks!

     

image (12).jpg

aramyan.h

Hi @leogabriel.banas01 ,

The moderators of this forum are experts in LSEG APIs and I am afraid we can't help with general coding related issues. If you are having any issues with your rdp request/response, please kindly detail it here and we will be happy to help.

Best regards,

Haykaz