Temperature change predictions

#import Libraries import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import sklearn

ETC_filepath='/work/archive/Environment_Temperature_change_E_All_Data_NOFLAG.csv' ETC_data=pd.read_csv(ETC_filepath) FAO_filepath='/work/archive/FAOSTAT_data_11-24-2020.csv' FAO_data=pd.read_csv(FAO_filepath)

ETC_data.head()

ETC_data.info()

ETC_data.describe()

ETC_data.columns

ETC_data.Element.value_counts()

ETC_data.Area.unique()

Morocco_ETC=ETC_data.loc[ETC_data.Area=='Morocco'] US_ETC=ETC_data.loc[ETC_data.Area=='United States of America'] France_ETC= ETC_data.loc[ETC_data.Area=='France']

Morocco_ETC=Morocco_ETC.reset_index(drop=True) US_ETC=US_ETC.reset_index(drop=True) France_ETC=France_ETC.reset_index(drop=True)

Morocco_ETC=Morocco_ETC.drop(["Area Code","Months Code","Element Code"], axis=1) US_ETC=US_ETC.drop(["Area Code","Months Code","Element Code"], axis=1) France_ETC=France_ETC.drop(["Area Code","Months Code","Element Code"], axis=1)

Morocco_ETC_N=Morocco_ETC.loc[Morocco_ETC.Months.isin(['January', 'February', 'March', 'April', 'May', 'June', 'July','August', 'September', 'October', 'November', 'December'])] US_ETC_N=US_ETC.loc[US_ETC.Months.isin(['January', 'February', 'March', 'April', 'May', 'June', 'July','August', 'September', 'October', 'November', 'December'])] France_ETC_N=France_ETC.loc[France_ETC.Months.isin(['January', 'February', 'March', 'April', 'May', 'June', 'July','August', 'September', 'October', 'November', 'December'])]

Morocco_ETC_Meteo=Morocco_ETC.loc[Morocco_ETC.Months=="Meteorological year"] US_ETC_Meteo=US_ETC.loc[US_ETC.Months=="Meteorological year"] France_ETC_Meteo=France_ETC.loc[France_ETC.Months=="Meteorological year"]

#made to calculate the average of temperature change in every month of the year def avg(list): return sum(list)/len(list) #both of the functions below create new dataframes out of the existing dataframes that are easier to handle def transform_data(df, element): d= {'Years':[i for i in range(1961,2020)] , element:[avg(df["Y"+str(i)].loc[df.Element==element]) for i in range(1961,2020)] } df1 = pd.DataFrame(data=d) return df1 def transform_data_meteo(df, element): d= {'Years':[i for i in range(1961,2020)] , element:[avg(df["Y"+str(i)].loc[df.Element==element]) for i in range(1961,2020)] } df1 = pd.DataFrame(data=d) return df1

Morocco_Temp_Change=transform_data(Morocco_ETC_N,'Temperature change') US_Temp_Change=transform_data(US_ETC_N,'Temperature change') France_Temp_Change=transform_data(France_ETC_N,'Temperature change')

Morocco_Meteo_Temp_Change=transform_data_meteo(Morocco_ETC_Meteo,'Temperature change') US_Meteo_Temp_Change=transform_data_meteo(US_ETC_Meteo,'Temperature change') France_Meteo_Temp_Change=transform_data_meteo(France_ETC_Meteo,'Temperature change')

Morocco_Meteo_Temp_Change['Years']=pd.to_datetime(Morocco_Meteo_Temp_Change["Years"],format="%Y") US_Meteo_Temp_Change['Years']=pd.to_datetime(US_Meteo_Temp_Change["Years"],format="%Y") France_Meteo_Temp_Change['Years']=pd.to_datetime(France_Meteo_Temp_Change["Years"],format="%Y")

Morocco_Temp_Change['Years']=pd.to_datetime(Morocco_Meteo_Temp_Change["Years"],format="%Y") US_Temp_Change['Years']=pd.to_datetime(US_Meteo_Temp_Change["Years"],format="%Y") France_Temp_Change['Years']=pd.to_datetime(France_Meteo_Temp_Change["Years"],format="%Y")

plt.figure(figsize=(20,10)) sns.lineplot(x=Morocco_Meteo_Temp_Change.Years,y=Morocco_Meteo_Temp_Change['Temperature change'], label="Morocco temperature change meteorology year") sns.lineplot(x=Morocco_Temp_Change.Years, y=Morocco_Temp_Change['Temperature change'],label="Morocco temperature change year")

plt.figure(figsize=(20,10)) sns.lineplot(x=Morocco_Meteo_Temp_Change.Years,y=Morocco_Meteo_Temp_Change['Temperature change'], label="Morocco") plt.legend

plt.figure(figsize=(20,10)) sns.lineplot(x=US_Meteo_Temp_Change.Years, y=US_Meteo_Temp_Change['Temperature change'], label="USA", color='red') plt.legend

plt.figure(figsize=(20,10)) sns.lineplot(x=France_Meteo_Temp_Change.Years, y=France_Meteo_Temp_Change['Temperature change'], color='green' ,label="France") plt.legend

from statsmodels.tsa.deterministic import CalendarFourier, DeterministicProcess from sklearn.linear_model import LinearRegression from xgboost import XGBRegressor from sklearn.model_selection import train_test_split def predict(df): df.set_index('Years', inplace=True) y=df['Temperature change'] fourier = CalendarFourier(freq="A", order=4) dp = DeterministicProcess( index= y.index, constant = True, order = 2, additional_terms=[fourier], drop = True ) X=dp.in_sample() idx_train, idx_test = train_test_split( y.index, test_size=0.2, shuffle=False, ) X_train, X_test = X.loc[idx_train, :], X.loc[idx_test, :] y_train, y_test = y.loc[idx_train], y.loc[idx_test] # Fit trend model model = LinearRegression(fit_intercept=False) model.fit(X_train, y_train) # Make predictions y_fit = pd.DataFrame( model.predict(X_train), index=y_train.index, ) y_pred = pd.DataFrame( model.predict(X_test), index=y_test.index, ) # Pivot wide to long (stack) and convert DataFrame to Series (squeeze) y_fit = y_fit.stack().squeeze() # trend from training set y_pred = y_pred.stack().squeeze() # trend from test set # Create residuals (the collection of detrended series) from the training set y_resid = y_train - y_fit # Train XGBoost on the residuals xgb = XGBRegressor() xgb.fit(X_train, y_resid) # Add the predicted residuals onto the predicted trends y_fit_boosted = xgb.predict(X_train) + y_fit y_pred_boosted = xgb.predict(X_test) + y_pred plt.figure(figsize=(16,8)) axs = y.plot(color='b', subplots=True, sharex=True) axs = y_fit_boosted.unstack().plot(color='r', subplots=True, sharex=True, ax=axs) axs = y_pred_boosted.unstack().plot(color='y', subplots=True, sharex=True, ax=axs)

predict(Morocco_Meteo_Temp_Change)

predict(US_Meteo_Temp_Change)

predict(France_Meteo_Temp_Change)