LSEG's SFI Climate Data in Workspace: A use-case evaluating public companies' Climate track record using Python

    	
            
import re # We'll use the `re` library to seperate numbers from words in strings.
import pandas as pd # this library is great for dataframe manipulations.
import plotly.graph_objects as go # `plotly` and its modules are useful for us to plot graphs.
import numpy as np # `numpy` in this case will be useful for us to plot graphs.

        
        Copy
    

    	
            
import lseg.data as ld
ld.open_session()

        
        Copy
    

    	
            
RIC = "MSFT.O" # SHEL.L, AAPL.O
scopeOfInterest = "1" # choice between "1", "2", "3", "1 and 2" or "1, 2 and 3"
setOfInterest = 1 # choice from 1 to 5
termOfInterest = "LT" # choice between "ST" and "LT"
sourceOfInterest = "LSEG" # choice between "LSEG" and "CDP"

        
        Copy
    

    	
            
scopeOfInterestFirstNumber = int(re.search(r'\d+', scopeOfInterest).group())
 
if termOfInterest == "ST":
    termNotOfInterest = "LT"
else:
    termNotOfInterest = "ST"
 
if sourceOfInterest == "LSEG":
    _sourceOfInterest = ""
elif sourceOfInterest == "CDP":
    _sourceOfInterest = sourceOfInterest

        
        Copy
    

    	
            
lstOfFlds = ["TR.CO2EquivalentEmissionsTotalMarketbased", "TR.CO2EmissionTotal"]
 
for i in range(1,4):
    lstOfFlds.append(f"TR.{_sourceOfInterest}CO2DirectScope{i}")
    lstOfFlds.append(f"TR.{_sourceOfInterest}CO2IndirectScope{i}")
lstOfFlds.append(f"TR.{_sourceOfInterest}CO2EmissionTotal")
lstOfFlds.append(f"TR.{_sourceOfInterest}TotalCO2EquivalentEmissionsScope1and2and3")
lstOfFlds.append(f"TR.{_sourceOfInterest}TotalCO2EquivalentEmissionScope1and2and3Marketbased")
lstOfFlds.append(f"TR.{_sourceOfInterest}{termOfInterest}GHGEmissionPercentageReductionTargetedSet{setOfInterest}")
lstOfFlds.append(f"TR.{_sourceOfInterest}{termOfInterest}PercentageofGHGEmissionCoveredbyTargetSet{setOfInterest}")
lstOfFlds.append(f"TR.{_sourceOfInterest}{termOfInterest}GHGEmissionScopeSet{setOfInterest}")
lstOfFlds.append(f"TR.{_sourceOfInterest}{termOfInterest}GHGEmissionBaseYearSet{setOfInterest}")
lstOfFlds.append(f"TR.{_sourceOfInterest}{termOfInterest}GHGEmissionTargetYearSet{setOfInterest}")
print(lstOfFlds)

        
        Copy
    

    	
            len(lstOfFlds)
        
        Copy
    

    	
            
df0 = ld.get_history(
    universe=[RIC],
    fields=lstOfFlds,
    start="1990-01-01",
    end="2025-01-01",
    header_type=ld.HeaderType.NAME_AND_TITLE,
).dropna(how='all')
df0.tail(3)

        
        Copy
    

    	
            
if scopeOfInterest == "1 and 2":
    df0[f"TR.{sourceOfInterest}CO2EQUIVALENTEMISSIONTOTAL|CO2 Equivalent Emissions Direct, Scope 1 and 2"] = df0[f"TR.{sourceOfInterest}CO2EQUIVALENTEMISSIONTOTAL|CO2 Equivalent Emissions Total"]

        
        Copy
    

    	
            print(list(df0.columns))
        
        Copy
    

    	
            
if sourceOfInterest == "LSEG":
    cols = [
        col for col in df0.columns
            if 'CO2EQUIVALENTEMISSIONSTOTALMARKETBASED' in col
            or "CO2EMISSIONTOTAL" in col
            or (
                'CDP' not in col # not in
                and f'Scope {scopeOfInterest}, ' not in col
                and f'Scope {scopeOfInterest} and ' not in col
                and f'Scope {scopeOfInterestFirstNumber+1}' not in col
                and f'Scope {scopeOfInterestFirstNumber+2}' not in col
                and f'Scope {scopeOfInterestFirstNumber-1}' not in col
                and f'Scope {scopeOfInterestFirstNumber-2}' not in col
                and f'{termNotOfInterest}GHGEMISSION' not in col
                and f'{termNotOfInterest}PERCENTAGE' not in col
                and (
                    f'Scope {scopeOfInterest}' in col
                    or f'Set{setOfInterest}' in col))]
 
if sourceOfInterest == "CDP":  # choice of "LSEG or "CDP"
    cols = [
        col for col in df0.columns
            if 'CO2EQUIVALENTEMISSIONSTOTALMARKETBASED' in col
            or "CO2EMISSIONTOTAL" in col
            or (
                'CDP' in col # in
                and f'Scope {scopeOfInterest}, ' not in col
                and f'Scope {scopeOfInterest} and ' not in col
                and f'Scope {scopeOfInterestFirstNumber+1}' not in col
                and f'Scope {scopeOfInterestFirstNumber+2}' not in col
                and f'Scope {scopeOfInterestFirstNumber-1}' not in col
                and f'Scope {scopeOfInterestFirstNumber-2}' not in col
                and f'{termNotOfInterest}GHGEMISSION' not in col
                and f'{termNotOfInterest}PERCENTAGE' not in col
                and (
                    f'Scope {scopeOfInterest}' in col
                    or f'Set{setOfInterest}' in col))]
 
print(len(cols))
cols

        
        Copy
    

    	
            
df1 = df0[cols]
df1.tail(5)

        
        Copy
    

    	
            
df2 = df1.replace('', pd._libs.missing.NA)
df3 = df2.dropna(how='all')
df3.tail(3)

        
        Copy
    

    	
            
df4 = df3.filter(like='PERCENTAGEOFGHGEMISSIONCOVEREDBYTARGETSET')
if df4.apply(pd.to_numeric, errors='coerce').dropna().gt(80).all().all():
    print("'GHGEmissionCoveredbyTarget' figures are above 80%. The higher this figure, the more reliable the results.")
    print("In this case, we consider them to be high enough to be reliable.")
else:
    print("Be weary of the fact that 'GHGEmissionCoveredbyTarget' is below 80%. The lower this figure, the less reliable the results.")

        
        Copy
    

    	
            
df5 = df3.copy()
df5.index = [np.int64(z) for z in pd.to_datetime(df5.index, errors='coerce').year.astype(object)] # keep only the years

        
        Copy
    

    	
            
baseEmissionYear = int(df3.filter(like='GHGEMISSIONBASEYEARSET').iloc[-1].values[0])
targetEmissionReductionYear = int(df3.filter(like='GHGEMISSIONTARGETYEARSET').iloc[-1].values[0])
baseEmission = df3[df3.index.year == baseEmissionYear].filter(like='CO2EMISSIONTOTAL').values[0][0]
targetReductionEmission = baseEmission * ((df3.filter(like='GHGEMISSIONPERCENTAGEREDUCTIONTARGETED').dropna().iloc[-1] / 100).iloc[0] * (df3.filter(like='PERCENTAGEOFGHGEMISSIONCOVEREDBYTARGET').dropna().iloc[-1] / 100).iloc[0])
targetEmission = baseEmission - targetReductionEmission
print(f"baseEmissionYear = {baseEmissionYear} & targetEmissionReductionYear = {targetEmissionReductionYear}")
print(f"baseEmission = {baseEmission} & targetReductionEmission = {targetReductionEmission} & targetEmission = {targetEmission}")

        
        Copy
    

    	
            
start_year = df3.T.filter(like=str(baseEmissionYear)).columns.values[0]
end_year = np.datetime64(
    f"{targetEmissionReductionYear}-{str(start_year)[5:7]}-{str(start_year)[8:10]}")
 
start_year = np.datetime64(start_year, 'ns')
end_year = np.datetime64(end_year, 'ns')
start_value = baseEmission
end_value = targetEmission
 
# Calculate the decay constant 'k' for exponential decay
# We use the formula for exponential decay: y(t) = y0 * exp(-k * (t - t0))
# Solve for 'k' using y(t) at the end point
# time_difference_years = (end_year - start_year).astype('timedelta64[Y]').astype(float)
# k = -np.log(end_value / start_value) / time_difference_years
 
if end_value / start_value == 0:
    k = -np.log(0.01) / (int(str(end_year)[:4]) - int(str(start_year)[:4]))  # Use a small value instead of zero to avoid log(0) issue
else:
    k = -np.log(end_value / start_value) / ((end_year - start_year).astype('timedelta64[Y]').astype(float))
 
# Generate years and corresponding values using exponential decay
years = np.arange(
    start_year.astype('datetime64[Y]').astype(int) + 1970,
    end_year.astype('datetime64[Y]').astype(int) + 1971)
values = start_value * np.exp(
    -k * (years - (start_year.astype('datetime64[Y]').astype(int) + 1970)))
 
decayDf = pd.DataFrame(data=values, index=years, columns=[f'Exponential Decay to target of {int(targetEmission)}'])
df6 = pd.concat([df5, decayDf])
 
# Create the plot
fig = go.Figure()
 
# Add the exponential decay line trace
fig.add_trace(
    go.Scatter(
        x=df6.index, y=df6[f'Exponential Decay to target of {int(targetEmission)}'], mode='lines',
        name=f'Exponential Decay to target of {int(targetEmission)}'))
 
# Set plot title and labels
fig.update_layout(
    title=f"{RIC} GHG Emissions (Base in {baseEmissionYear} and Target in {targetEmissionReductionYear}) in CO2 Tons",
    xaxis_title="Year",
    yaxis_title="CO2 Tons",
    template="plotly_dark"  # Optional: You can use different templates, such as 'plotly', 'ggplot2', etc.
)
 
# Add the dots representing the actual CO2 data from df3
fig.add_trace(go.Scatter(
    x=df6.index, 
    y=df6[df6.filter(like="CO2EMISSIONTOTAL").columns[0]],
    mode='lines+markers', 
    name='CO2 Equivalents Emission Total',
    marker=dict(color='red', size=8)  # Customize the dot color and size
))
 
fig.add_trace(go.Scatter(
    x=df6.index, 
    y=df6[df6.filter(like="TR.CO2EQUIVALENTEMISSIONSTOTALMARKETBASED").columns[0]],
    mode='lines+markers', 
    name='CO2 Equivalent Emissions Total Market-based',
    marker=dict(color='grey', size=8)  # Customize the dot color and size
))
 
# Show the plot
fig.show()

        
        Copy
    

    	
            ld.close_session()
        
        Copy
    

    	
            
ld.open_session()
df = GHGEmissionsBaseVsTargetUsingLSEGWorkspace(
    RIC="SHEL.L", # MSFT.O, AAPL.O, SHEL.L, LVMH.PA
    scope="1", # choice between "1", "2", "3", "1 and 2" or "1, 2 and 3"
    set=1, # choice from 1 to 5
    term="ST", # choice between "ST" and "LT"
    source="LSEG") # choice between "LSEG" and "CDP"
ld.close_session()

        
        Copy