How to use bezoek method in SeleniumBase

Best Python code snippet using SeleniumBase

google_loader.py

Source:google_loader.py

1import pandas as pd2import mezuro_preprocessing as mp3import math4import copy5import datetime as dt6'''7Reduce normal mobility by a factor based on Google mobility data8Input: Mezuro mobility dataframe, historical days ago on which the prediction should be based9Output: Mezuro mobility dataframe where mobility is reduced by prediction of the Google rate10Warning: both functions take quite long to execute (preprocess: approx. 20s per date; apply: approx. 2 min. per date)11'''12#Load Google data13google_mobility=pd.read_csv(14            'data/2020_NL_Region_Mobility_Report.csv'15            ).rename(columns={'retail_and_recreation_percent_change_from_baseline': 'retail',16                         'grocery_and_pharmacy_percent_change_from_baseline': 'grocery',17                         'parks_percent_change_from_baseline': 'parks',18                         'transit_stations_percent_change_from_baseline': 'transit',19                         'workplaces_percent_change_from_baseline': 'workplaces',20                         'residential_percent_change_from_baseline': 'residential'})21#Re-format province and municipality names to match Mezuro records22google_mobility["sub_region_1"] = google_mobility["sub_region_1"].replace(23        ['North Holland','South Holland','North Brabant'],24        ['Noord-Holland','Zuid-Holland','Noord-Brabant']25        )26google_mobility["sub_region_2"] = google_mobility["sub_region_2"].replace(27    ['Government of Rotterdam','Government of Amsterdam','s-Hertogenbosch','The Hague','Eijsden','Reeuwijk','Flushing'],28    ['Rotterdam','Amsterdam',"'s-Hertogenbosch","'s-Gravenhage",'Eijsden-Margraten','Bodegraven-Reeuwijk','Vlissingen']29    )30google_mobility.loc[(google_mobility["sub_region_1"] == 'Limburg') & (google_mobility["sub_region_2"] == 'Bergen'), ("sub_region_2")] = 'Bergen (L.)'31google_mobility.loc[(google_mobility["sub_region_1"] == 'Noord-Holland')& (google_mobility["sub_region_2"] == 'Bergen'), ("sub_region_2")] = 'Bergen (NH.)'32# The gemeente naming that must be used in the outputed file33year_gemeenten_used = '2020'34def mezuro_convert_to_date(mobility,y = year_gemeenten_used):35    36    mobility = mobility.reset_index()37    mobility_overig = mobility.loc[mobility['woon'] == 'Overige gebieden']38    mobility_known = mobility.loc[mobility['woon'] != 'Overige gebieden']39    mobility_known['woon'] = mobility_known['woon'].map(lambda name: mp.koppeltabel.loc[name,'rivm'+y])40    mobility_known['bezoek'] = mobility_known['bezoek'].map(lambda name: mp.koppeltabel.loc[name,'rivm'+y])41    mobility_overig['bezoek'] = mobility_overig['bezoek'].map(lambda name: mp.koppeltabel.loc[name,'rivm'+y])42    mobility = mobility_known.append(mobility_overig)43    '''44    for index, row in mp.gemeente2gemeente.iterrows():45        print(index)46        if index[0] == 'Overige gebieden':47            mobility.rename(index={index: (index[0] ,mp.koppeltabel.loc[index[1],'rivm'+y] ,index[2]) })48        else:49            mobility.rename(index={index: (mp.koppeltabel.loc[index[0],'rivm'+y] ,mp.koppeltabel.loc[index[1],'rivm'+y] ,index[2]) })50    mobility = mobility.reset_index51    mobility = mobility[mobility['woon'] != mobility['bezoek']]52    '''53    mobility = mobility.set_index(['woon','bezoek','datum'])54    mobility = mobility.groupby(['woon','bezoek','datum']).agg({'bezoek_gemeente_id':'mean','woon_gemeente_id':'mean',  'totaal_aantal_bezoekers':'sum', 'incidentele_bezoeker':'sum', 'regelmatige_bezoeker':'sum', 'frequente_bezoeker':'sum' })55    return mobility56#mezuro_updated = mezuro_convert_to_date(mp.gemeente2gemeente)57def preprocess_rates(start_date,end_date):58    #Transform start and today date into datetime object:59    date_format = '%d-%m-%Y'60    start_date_number = dt.datetime.strptime(start_date,date_format)61    end_date_number = dt.datetime.strptime(end_date,date_format)62    63    #Create empty to-be-filled dataframes64    Reduction_rates_google = pd.DataFrame(columns = ['country_region_code',	65                                                     'country_region',	66                                                     'sub_region_1',	67                                                     'sub_region_2',	68                                                     'metro_area',	69                                                     'iso_3166_2_code',	70                                                     'census_fips_code',	71                                                     'date',72                                                     'retail',	73                                                     'grocery',	74                                                     'parks',	75                                                     'transit',76                                                     'workplaces',77                                                     'residential'])78    79    Reduction_rates_google_prov = pd.DataFrame(columns = ['country_region_code',	80                                                     'country_region',	81                                                     'sub_region_1',	82                                                     'sub_region_2',	83                                                     'metro_area',	84                                                     'iso_3166_2_code',	85                                                     'census_fips_code',	86                                                     'date',87                                                     'retail',	88                                                     'grocery',	89                                                     'parks',	90                                                     'transit',91                                                     'workplaces',92                                                     'residential'])93    94    95    for t in range(1, (end_date_number - start_date_number).days + 2):96        #Calculate new date97        day_difference = dt.timedelta(days = t-1)98        current_date_number = start_date_number + day_difference99        current_date = current_date_number.strftime('%d-%m-%Y')100        current_date_google_format = current_date_number.strftime('%Y-%m-%d')101        #Extract part of Google dataframe corresponding to the current date (first only municipalities, then only provinces)102        google_mob2 = google_mobility.loc[google_mobility["sub_region_2"].notnull()].groupby('date').get_group(current_date_google_format)103        google_mob_prov = google_mobility.loc[(google_mobility["sub_region_2"].isnull()) & (google_mobility["sub_region_1"].notnull())].groupby('date').get_group(current_date_google_format)104        row_NL = google_mobility.loc[(google_mobility["sub_region_1"].isnull()) & (google_mobility["date"] == current_date_google_format) & google_mobility["sub_region_2"].isnull()]                 105        106        print(current_date)107        108        #Fill up missing values in the province data109        for index,row in google_mob_prov.iterrows():110            google_mob_prov.at[index,'date'] = current_date111            for col in ['retail','grocery','parks','transit','workplaces','residential']:112                if math.isnan(row[col]):113                    reduction_value = row_NL[col]114                    google_mob_prov.at[index,col] = reduction_value115        116        #Fill up missing values in the municipality data117        for index,row in google_mob2.iterrows():118            row_province = google_mobility.loc[(google_mobility["sub_region_1"] == row["sub_region_1"]) & (google_mobility["date"] == current_date_google_format) & google_mobility["sub_region_2"].isnull()]119            google_mob2.at[index,'date'] = current_date120            for col in ['retail','grocery','parks','transit','workplaces','residential']:121                if math.isnan(row[col]):122                    reduction_value = row_province[col]123                    if math.isnan(reduction_value):124                        reduction_value = row_NL[col]125                    google_mob2.at[index,col] = reduction_value126        127        #Add filled-up data frames128        Reduction_rates_google = Reduction_rates_google.append(google_mob2)129        Reduction_rates_google_prov = Reduction_rates_google_prov.append(google_mob_prov)130        131        #Include municipalities that do not have an entry in the Google data for the current date132        for index, row in mp.koppeltabel.iterrows():133            if len(Reduction_rates_google.loc[(Reduction_rates_google["sub_region_2"] == row["rivm"+year_gemeenten_used]) & (Reduction_rates_google["date"] == current_date)]) == 0:134                province = mp.gemeente_shapes_old.at[index,'prov_name']135                df_help_add = copy.copy(Reduction_rates_google_prov.groupby("sub_region_1").get_group(province).groupby("date").get_group(current_date))136                df_help_add["sub_region_2"] = df_help_add["sub_region_2"].fillna(row["rivm"+year_gemeenten_used])137                Reduction_rates_google = Reduction_rates_google.append(df_help_add)138    139    print(len(Reduction_rates_google))140    #Include missing municipalities from Mezuro data:141    #First: get list of municipalities in Google data:142    df_help_gemeentes = Reduction_rates_google.groupby('date').get_group(end_date)    143    for index, row in mp.koppeltabel.iterrows():144        if len(Reduction_rates_google.loc[Reduction_rates_google["sub_region_2"] == row['rivm'+year_gemeenten_used]]) == 0:145            province = mp.gemeente_shapes.at[index,'prov_name']146            df_help_add = copy.copy(Reduction_rates_google_prov.groupby("sub_region_1").get_group(province))147            df_help_add["sub_region_2"] = df_help_add["sub_region_2"].fillna(row['rivm'+year_gemeenten_used])148            Reduction_rates_google = Reduction_rates_google.append(df_help_add)149            #Note: removal of rows might not be as handy with regard to merging muniipalities150    print(len(Reduction_rates_google))            151    #Remove rows if municipality in Google data is not in rivm data:152    for index,row in df_help_gemeentes.iterrows():153        if len(mp.koppeltabel.loc[mp.koppeltabel['rivm'+year_gemeenten_used] == row["sub_region_2"]]) == 0:154            Reduction_rates_google = Reduction_rates_google[Reduction_rates_google["sub_region_2"] != row['sub_region_2']]155    print(len(Reduction_rates_google))156    return Reduction_rates_google, Reduction_rates_google_prov157    #Apply the preprocessed Google mobility rates to the Mezuro data to obtain an estimation of the actual mobility158def apply_rates(start_date,end_date,Reduction_rates_march,Reduction_rates):159    date_format = '%d-%m-%Y'160    start_date_number = dt.datetime.strptime(start_date,date_format)161    end_date_number = dt.datetime.strptime(end_date,date_format)162    163    #Create new mobility file based on data from March 1-14164    165    #First: determine which days are which:166    list_day_2019 = [['04-03-2019','11-03-2019'],167                ['05-03-2019','12-03-2019'],168                ['06-03-2019','13-03-2019'],169                ['07-03-2019','14-03-2019'],170                ['01-03-2019','08-03-2019'],171                ['02-03-2019','09-03-2019'],172                ['03-03-2019','10-03-2019']173                ]174    175    list_day_2020 = [['02-03-2020','09-03-2020'],176                ['03-03-2020','10-03-2020'],177                ['04-03-2020','11-03-2020'],178                ['05-03-2020','12-03-2020'],179                ['06-03-2020','13-03-2020'],180                ['07-03-2020','14-03-2020'],181                ['01-03-2020','08-03-2020']182                ]183    184    df_mobility = pd.DataFrame(columns = ['woon',185                                   'bezoek',186                                   'datum',187                                   'bezoek_gemeente_id',188                                   'woon_gemeente_id',189                                   'totaal_aantal_bezoekers',190                                   'incidentele_bezoeker',191                                   'regelmatige_bezoeker',192                                   'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek','datum'])193    194    for t in range(0,(end_date_number - start_date_number).days + 1):195        day_difference = dt.timedelta(days = t)196        current_date_number = start_date_number + day_difference197        current_date = current_date_number.strftime('%d-%m-%Y')198        199        print(current_date)200        201        weekday = current_date_number.weekday()202        df_help_collect = pd.DataFrame(columns = ['woon',203                                       'bezoek',204                                       'datum',205                                       'bezoek_gemeente_id',206                                       'woon_gemeente_id',207                                       'totaal_aantal_bezoekers',208                                       'incidentele_bezoeker',209                                       'regelmatige_bezoeker',210                                       'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek','datum'])211        for index, i in enumerate(list_day_2019[weekday]):212            print(index,i)213            df_help_date = copy.copy(mezuro_updated.groupby("datum").get_group(i))214            215            for index2, row in df_help_date.iterrows():216                '''217                    #Make exception for overige gebieden: in that case, take mobility rates from destination gemeente - should probably be different in future iterations of the model218                df_help_date = df_help_date.reset_index()219                df_help_date_overig = df_help_date.loc[df_help_date['woon'] == 'Overige gebieden']220                df_help_date_known = df_help_date.loc[df_help_date['woon'] != 'Overige gebieden']221                df_help_date_overig['incidentele_bezoeker'] = df_help_date_overig['incidentele_bezoeker'].map(lambda value: value / (1+ float((Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == df_help_date_overig['bezoek']) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])])['retail']) / 100) * (1+float((Reduction_rates.loc[(Reduction_rates["sub_region_2"] == df_help_date_overig['bezoek']) &  (Reduction_rates["date"] == current_date)])['retail']) / 100) )222                df_help_date_overig['regelmatige_bezoeker'] = df_help_date_overig['regelmatige_bezoeker'].map(lambda value: value / (1+ float((Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == df_help_date_overig['bezoek']) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])])['retail']) / 100) * (1+float((Reduction_rates.loc[(Reduction_rates["sub_region_2"] == df_help_date_overig['bezoek']) &  (Reduction_rates["date"] == current_date)])['retail']) / 100) )223                df_help_date_overig['frequente_bezoeker'] = df_help_date_overig['frequente_bezoeker'].map(lambda value: value / (1+ float((Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == df_help_date_overig['bezoek']) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])])['workplaces']) / 100) * (1+float((Reduction_rates.loc[(Reduction_rates["sub_region_2"] == df_help_date_overig['bezoek']) &  (Reduction_rates["date"] == current_date)])['workplaces']) / 100) )224                df_help_date_known['incidentele_bezoeker'] = df_help_date_known['incidentele_bezoeker'].map(lambda value: value / (1+ float((Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == df_help_date_overig['woon']) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])])['retail']) / 100) * (1+float((Reduction_rates.loc[(Reduction_rates["sub_region_2"] == df_help_date_overig['woon']) &  (Reduction_rates["date"] == current_date)])['retail']) / 100) )225                df_help_date_known['regelmatige_bezoeker'] = df_help_date_known['regelmatige_bezoeker'].map(lambda value: value / (1+float((Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == df_help_date_overig['woon']) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])])['retail']) / 100) * (1+float((Reduction_rates.loc[(Reduction_rates["sub_region_2"] == df_help_date_overig['woon']) &  (Reduction_rates["date"] == current_date)])['retail']) / 100) )226                df_help_date_known['frequente_bezoeker'] = df_help_date_known['frequente_bezoeker'].map(lambda value: value / (1+ float((Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == df_help_date_overig['woon']) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])])['workplaces']) / 100) * (1+float((Reduction_rates.loc[(Reduction_rates["sub_region_2"] == df_help_date_overig['woon']) &  (Reduction_rates["date"] == current_date)])['workplaces']) / 100) )227               228                df_help_date = df_help_date_known.append(df_help_date_overig)229                df_help_date['totaal_aantal_bezoekers'] = df_help_date['incidentele_bezoeker'] + df_help_date['regelmatige_bezoeker'] + df_help_date['frequente_bezoeker']230                df_help_date = df_help_date.set_index(['woon','bezoek','datum'])231                232                    233                '''234                if index2[0] == 'Overige gebieden':235                    rivm_gemeente = index2[1]236                    #rivm_gemeente = mp.koppeltabel.at[index2[1],'rivm'+year_gemeenten_used]237                else:238                    #rivm_gemeente = mp.koppeltabel.at[index2[0],'rivm'+year_gemeenten_used]239                    rivm_gemeente = index2[0]240    241                rate_row = Reduction_rates_march.loc[(Reduction_rates_march["sub_region_2"] == rivm_gemeente) &  (Reduction_rates_march["date"] == list_day_2020[weekday][index])]242                rate_row2 = Reduction_rates.loc[(Reduction_rates["sub_region_2"] == rivm_gemeente) &  (Reduction_rates["date"] == current_date)]243    244                df_help_date.at[index2,'incidentele_bezoeker'] /= ((1 + float(rate_row["retail"]) / 100)  / (1 + float(rate_row2["retail"]) / 100) )245                df_help_date.at[index2,'regelmatige_bezoeker'] /= ((1 + float(rate_row["retail"]) / 100) / (1 + float(rate_row2["retail"]) / 100) )246                df_help_date.at[index2,'frequente_bezoeker'] /= ((1 + float(rate_row["workplaces"]) / 100) / (1 + float(rate_row2["workplaces"]) / 100) )247                #df_help_date.at[index2,'totaal_aantal_bezoekers'] = df_help_date.at[index2,'incidentele_bezoeker'] + df_help_date.at[index2,'regelmatige_bezoeker'] + df_help_date.at[index2,'frequente_bezoeker']248            249            df_help_collect = df_help_collect.append(df_help_date)250        251        df_help_collect = df_help_collect.groupby(['woon','bezoek']).agg({'bezoek_gemeente_id':'mean','woon_gemeente_id':'mean','totaal_aantal_bezoekers':'mean', 'incidentele_bezoeker':'mean', 'regelmatige_bezoeker':'mean', 'frequente_bezoeker':'mean' })252        df_help_collect = df_help_collect.reset_index()253        df_help_collect["datum"] = current_date254        df_help_collect = df_help_collect.set_index(['woon','bezoek','datum'])255        df_mobility = df_mobility.append(df_help_collect)256    257    df_mobility['totaal_aantal_bezoekers'] = df_mobility['incidentele_bezoeker'] + df_mobility['regelmatige_bezoeker'] + df_mobility['frequente_bezoeker']258    '''259    Mobility_df = copy.copy(df_mobility)260    '''261    '''262    #Finally, apply new reduction rates!263    for index, row in Mobility_df.iterrows():264        if index[0] == 'Overige gebieden':265            rivm_gemeente = mp.koppeltabel.at[index[1],'rivm'+year_gemeenten_used]266            print(index)267        else:268            rivm_gemeente = mp.koppeltabel.at[index[0],'rivm'+year_gemeenten_used]269        rate_row = Reduction_rates.loc[(Reduction_rates["sub_region_2"] == rivm_gemeente) &  (Reduction_rates["date"] == index[2])]270        Mobility_df.at[index,'incidentele_bezoeker'] *= (1 + rate_row["retail"] / 100) 271        Mobility_df.at[index,'regelmatige_bezoeker'] *= (1 + rate_row["retail"] / 100)272        Mobility_df.at[index,'frequente_bezoeker'] *= (1 + rate_row["workplaces"] / 100)273        Mobility_df.at[index,'totaal_aantal_bezoekers'] = Mobility_df.at[index,'incidentele_bezoeker'] + Mobility_df.at[index,'regelmatige_bezoeker'] + Mobility_df.at[index,'frequente_bezoeker']274    275    return Mobility_df276    '''277    return df_mobility278    #Create new mobility file based on data from March 1-14 without Google rates279def create_mobility_per_date(start_date,end_date):280    date_format = '%d-%m-%Y'281    start_date_number = dt.datetime.strptime(start_date,date_format)282    end_date_number = dt.datetime.strptime(end_date,date_format)283    284    285    #First: determine which days are which:286    list_day_2019 = [['04-03-2019','11-03-2019'],287                ['05-03-2019','12-03-2019'],288                ['06-03-2019','13-03-2019'],289                ['07-03-2019','14-03-2019'],290                ['01-03-2019','08-03-2019'],291                ['02-03-2019','09-03-2019'],292                ['03-03-2019','10-03-2019']293                ]294    295    list_day_2020 = [['02-03-2020','09-03-2020'],296                ['03-03-2020','10-03-2020'],297                ['04-03-2020','11-03-2020'],298                ['05-03-2020','12-03-2020'],299                ['06-03-2020','13-03-2020'],300                ['07-03-2020','14-03-2020'],301                ['01-03-2020','08-03-2020']302                ]303    304    df_mobility = pd.DataFrame(columns = ['woon',305                                   'bezoek',306                                   'datum',307                                   'bezoek_gemeente_id',308                                   'woon_gemeente_id',309                                   'totaal_aantal_bezoekers',310                                   'incidentele_bezoeker',311                                   'regelmatige_bezoeker',312                                   'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek','datum'])313    314    for t in range(0,(end_date_number - start_date_number).days + 1):315        day_difference = dt.timedelta(days = t)316        current_date_number = start_date_number + day_difference317        current_date = current_date_number.strftime('%d-%m-%Y')318        print(current_date)319        weekday = current_date_number.weekday()320        df_help_collect = pd.DataFrame(columns = ['woon',321                                       'bezoek',322                                       'datum',323                                       'bezoek_gemeente_id',324                                       'woon_gemeente_id',325                                       'totaal_aantal_bezoekers',326                                       'incidentele_bezoeker',327                                       'regelmatige_bezoeker',328                                       'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek','datum'])329        for index, i in enumerate(list_day_2019[weekday]):330            df_help_date = mp.gemeente2gemeente.groupby("datum").get_group(i)331            df_help_collect = df_help_collect.append(df_help_date)332        df_help_collect = df_help_collect.groupby(['woon','bezoek']).agg({'totaal_aantal_bezoekers':'mean', 'incidentele_bezoeker':'mean', 'regelmatige_bezoeker':'mean', 'frequente_bezoeker':'mean' })333        df_help_collect = df_help_collect.reset_index()334        df_help_collect["datum"] = current_date335        df_help_collect = df_help_collect.set_index(['woon','bezoek','datum'])336        df_mobility = df_mobility.append(df_help_collect)337    338    Mobility_df = copy.copy(df_mobility)339    return Mobility_df340def create_CBS_OD_matrix():341    CBS_work_mobility=pd.read_csv(342            'data/Woon_werkafstand_werknemers__regio.csv',delimiter = ';').rename(columns={'Banen van werknemers (x 1 000)':'banen'})343    344    CBS_work_mobility["Woonregio's"] = CBS_work_mobility["Woonregio's"].replace(345    ['Groningen (gemeente)','Utrecht (gemeente)','Hengelo (O.)',"'s-Gravenhage (gemeente)",'Beek (L.)','Laren (NH.)','Middelburg (Z.)','Rijswijk (ZH.)','Stein (L.)'],346    ['Groningen','Utrecht','Hengelo',"'s-Gravenhage",'Beek','Laren','Middelburg','Rijswijk','Stein']347    )    348    CBS_work_mobility["Werkregio's"] = CBS_work_mobility["Werkregio's"].replace(349    ['Groningen (gemeente)','Utrecht (gemeente)','Hengelo (O.)',"'s-Gravenhage (gemeente)",'Beek (L.)','Laren (NH.)','Middelburg (Z.)','Rijswijk (ZH.)','Stein (L.)'],350    ['Groningen','Utrecht','Hengelo',"'s-Gravenhage",'Beek','Laren','Middelburg','Rijswijk','Stein']351    )352    CBS_work_mobility['banen'] = CBS_work_mobility['banen'].astype('float')353    CBS_work_mobility = CBS_work_mobility.set_index(["Woonregio's","Werkregio's"])354    355    df_mobility = pd.DataFrame(columns = ['woon',356                                   'bezoek',357                                   'bezoek_gemeente_id',358                                   'woon_gemeente_id',359                                   'totaal_aantal_bezoekers',360                                   'incidentele_bezoeker',361                                   'regelmatige_bezoeker',362                                   'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek'])363    364    for index, row in CBS_work_mobility.iterrows():365        if index[0] != index[1] and index[0] in mp.gemeenten_list.index and index[1] in mp.gemeenten_list.index:366            if row['banen'] != 0:367                new_row = {'woon':index[0],368                           'bezoek':index[1],369                           'bezoek_gemeente_id':mp.gemeenten_list.at[index[0],'Gemeentecode'],370                           'woon_gemeente_id':mp.gemeenten_list.at[index[1],'Gemeentecode'],371                           'totaal_aantal_bezoekers':row['banen'] * 1000,372                           'incidentele_bezoeker':0,373                           'regelmatige_bezoeker':0,374                           'frequente_bezoeker':row['banen'] * 1000375                           }376                df_mobility = df_mobility.append(new_row, ignore_index = True)377                print(index[0],index[1])378    return df_mobility379def preprocess_rates_CBS(start_date,end_date):380    #Transform start and today date into datetime object:381    date_format = '%d-%m-%Y'382    start_date_number = dt.datetime.strptime(start_date,date_format)383    end_date_number = dt.datetime.strptime(end_date,date_format)384    385    #Create empty to-be-filled dataframes386    Reduction_rates_google = pd.DataFrame(columns = ['country_region_code',	387                                                     'country_region',	388                                                     'sub_region_1',	389                                                     'sub_region_2',	390                                                     'metro_area',	391                                                     'iso_3166_2_code',	392                                                     'census_fips_code',	393                                                     'date',394                                                     'retail',	395                                                     'grocery',	396                                                     'parks',	397                                                     'transit',398                                                     'workplaces',399                                                     'residential'])400    401    Reduction_rates_google_prov = pd.DataFrame(columns = ['country_region_code',	402                                                     'country_region',	403                                                     'sub_region_1',	404                                                     'sub_region_2',	405                                                     'metro_area',	406                                                     'iso_3166_2_code',	407                                                     'census_fips_code',	408                                                     'date',409                                                     'retail',	410                                                     'grocery',	411                                                     'parks',	412                                                     'transit',413                                                     'workplaces',414                                                     'residential'])415    416    417    for t in range(1, (end_date_number - start_date_number).days + 2):418        #Calculate new date419        day_difference = dt.timedelta(days = t-1)420        current_date_number = start_date_number + day_difference421        current_date = current_date_number.strftime('%d-%m-%Y')422        current_date_google_format = current_date_number.strftime('%Y-%m-%d')423        #Extract part of Google dataframe corresponding to the current date (first only municipalities, then only provinces)424        google_mob2 = google_mobility.loc[google_mobility["sub_region_2"].notnull()].groupby('date').get_group(current_date_google_format)425        google_mob_prov = google_mobility.loc[(google_mobility["sub_region_2"].isnull()) & (google_mobility["sub_region_1"].notnull())].groupby('date').get_group(current_date_google_format)426        row_NL = google_mobility.loc[(google_mobility["sub_region_1"].isnull()) & (google_mobility["date"] == current_date_google_format) & google_mobility["sub_region_2"].isnull()]                 427        428        print(current_date)429        430        #Fill up missing values in the province data431        for index,row in google_mob_prov.iterrows():432            google_mob_prov.at[index,'date'] = current_date433            for col in ['retail','grocery','parks','transit','workplaces','residential']:434                if math.isnan(row[col]):435                    reduction_value = row_NL[col]436                    google_mob_prov.at[index,col] = reduction_value437        438        #Fill up missing values in the municipality data439        for index,row in google_mob2.iterrows():440            row_province = google_mobility.loc[(google_mobility["sub_region_1"] == row["sub_region_1"]) & (google_mobility["date"] == current_date_google_format) & google_mobility["sub_region_2"].isnull()]441            google_mob2.at[index,'date'] = current_date442            for col in ['retail','grocery','parks','transit','workplaces','residential']:443                if math.isnan(row[col]):444                    reduction_value = row_province[col]445                    if math.isnan(reduction_value):446                        reduction_value = row_NL[col]447                    google_mob2.at[index,col] = reduction_value448        449        #Add filled-up data frames450        Reduction_rates_google = Reduction_rates_google.append(google_mob2)451        Reduction_rates_google_prov = Reduction_rates_google_prov.append(google_mob_prov)452        453        #Include municipalities that do not have an entry in the Google data for the current date454        for index, row in mp.koppeltabel.iterrows():455            if len(Reduction_rates_google.loc[(Reduction_rates_google["sub_region_2"] == row["rivm"+year_gemeenten_used]) & (Reduction_rates_google["date"] == current_date)]) == 0:456                province = mp.gemeente_shapes_old.at[index,'prov_name']457                df_help_add = copy.copy(Reduction_rates_google_prov.groupby("sub_region_1").get_group(province).groupby("date").get_group(current_date))458                df_help_add["sub_region_2"] = df_help_add["sub_region_2"].fillna(row["rivm"+year_gemeenten_used])459                Reduction_rates_google = Reduction_rates_google.append(df_help_add)460    461    print(len(Reduction_rates_google))462    #Include missing municipalities from Mezuro data:463    #First: get list of municipalities in Google data:464    df_help_gemeentes = Reduction_rates_google.groupby('date').get_group(end_date)    465    for index, row in mp.koppeltabel.iterrows():466        if len(Reduction_rates_google.loc[Reduction_rates_google["sub_region_2"] == row['rivm'+year_gemeenten_used]]) == 0:467            province = mp.gemeente_shapes.at[index,'prov_name']468            df_help_add = copy.copy(Reduction_rates_google_prov.groupby("sub_region_1").get_group(province))469            df_help_add["sub_region_2"] = df_help_add["sub_region_2"].fillna(row['rivm'+year_gemeenten_used])470            Reduction_rates_google = Reduction_rates_google.append(df_help_add)471            #Note: removal of rows might not be as handy with regard to merging muniipalities472    print(len(Reduction_rates_google))            473    #Remove rows if municipality in Google data is not in rivm data:474    for index,row in df_help_gemeentes.iterrows():475        if len(mp.koppeltabel.loc[mp.koppeltabel['rivm'+year_gemeenten_used] == row["sub_region_2"]]) == 0:476            Reduction_rates_google = Reduction_rates_google[Reduction_rates_google["sub_region_2"] != row['sub_region_2']]477    print(len(Reduction_rates_google))478    return Reduction_rates_google, Reduction_rates_google_prov479def apply_rates_CBS(start_date,end_date,Reduction_rates,df):480    date_format = '%d-%m-%Y'481    start_date_number = dt.datetime.strptime(start_date,date_format)482    end_date_number = dt.datetime.strptime(end_date,date_format)483    484    Reduction_rates = Reduction_rates.set_index(['sub_region_2','date'])485    df_mobility = pd.DataFrame(columns = ['woon',486                                'bezoek',487                                'datum',488                                'bezoek_gemeente_id',489                                'woon_gemeente_id',490                                'totaal_aantal_bezoekers',491                                'incidentele_bezoeker',492                                'regelmatige_bezoeker',493                                'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek','datum'])494 495    496    for t in range(0,(end_date_number - start_date_number).days + 1):497        day_difference = dt.timedelta(days = t)498        current_date_number = start_date_number + day_difference499        current_date = current_date_number.strftime('%d-%m-%Y')500        print('Current date:',current_date)501        df_help_date = copy.copy(df).set_index(['woon','bezoek'])502        503        504        #Determine weekend-factor:505        Weekday_factor = 1506        '''507        508        if current_date_number.weekday() == 5:509            Weekday_factor = .36*6.2 / 31510        if current_date_number.weekday() == 6:511            Weekday_factor = .27*6.2 / 31512        if current_date_number.weekday() != 5 and  current_date_number.weekday() != 6:513            Weekday_factor = 1 - (.36+.27)*6.2 / 31514        '''515        516        for index2, row in df_help_date.iterrows():517            #print(index2)518            #Make exception for overige gebieden: in that case, take mobility rates from destination gemeente - should probably be different in future iterations of the model519            if index2[0] == 'Overige gebieden':520                rivm_gemeente = mp.koppeltabel.at[index2[1],'rivm2020']521            else:522                #rivm_gemeente = mp.koppeltabel.at[index2[0],'rivm2020']523                rivm_gemeente = index2[0]524            Target_rate_retail = Reduction_rates.at[(rivm_gemeente,current_date),'retail']525            Target_rate_workplaces = Reduction_rates.at[(rivm_gemeente,current_date),'workplaces']                526            527            528            df_help_date.at[index2,'incidentele_bezoeker']  *= (1 + Target_rate_retail / 100)  * Weekday_factor529            df_help_date.at[index2,'regelmatige_bezoeker']  *=  (1 + Target_rate_retail / 100) * Weekday_factor530            df_help_date.at[index2,'frequente_bezoeker']  *=  (1 + Target_rate_workplaces / 100) * Weekday_factor531        532        df_help_date['datum'] = current_date533        df_help_date['totaal_aantal_bezoekers'] = df_help_date['incidentele_bezoeker'] + df_help_date['regelmatige_bezoeker'] + df_help_date['frequente_bezoeker']534        #df_help_date = df_help_date.reset_index535        #df_help_date = df_help_date.set_index(['woon','bezoek','datum'])536        537        df_help_date = df_help_date.reset_index()538        539        df_mobility = df_mobility.append(df_help_date)540        541    542    return df_mobility.set_index(['woon','bezoek','datum'])543        544def create_2019_CBS(df):545    start_date = '01-03-2019'546    end_date = '14-03-2019'547    start_date_nr = dt.datetime.strptime(start_date,'%d-%m-%Y')548    end_date_nr = dt.datetime.strptime(end_date,'%d-%m-%Y')549    550    df_mobility = pd.DataFrame(columns = ['woon',551                                'bezoek',552                                'datum',553                                'bezoek_gemeente_id',554                                'woon_gemeente_id',555                                'totaal_aantal_bezoekers',556                                'incidentele_bezoeker',557                                'regelmatige_bezoeker',558                                'frequente_bezoeker'], dtype = float).set_index(['woon','bezoek','datum'])559 560    561    for t in range(0,14):562        Current_date_nr = start_date_nr + dt.timedelta(days = t)563        Current_date = Current_date_nr.strftime('%d-%m-%Y')564        565        df_HELP = copy.copy(df)566        df_HELP['datum'] = Current_date567        df_mobility = df_mobility.append(df_HELP)568    return df_mobility.set_index(['woon','bezoek','datum'])569        ...

synthesevraag2.py

Source:synthesevraag2.py

1from random import randint2def basisscore_berekenen(naam, aantal_bezoek, geboortejaar):3    basisscore = 04    komt_voor = ""5    som = 06    for i in range(len(naam)):7        if naam[i] in "cinema":8            #komt_voor += str(naam[i])9            som += (ord(naam[i]) * (i + 1))10    som += geboortejaar11    #som *= aantal_bezoek12    return som13def gewonnen_tickets(randomgetal):14    som_tickets = 015    string_random = str(randomgetal)16    for letter in string_random:17        som_tickets += int(letter)18        randomgetall = int(string_random)19    return som_tickets20def is_slechteklant(snacks, aantal_bezoek):21    if snacks.lower() == "n" and (aantal_bezoek == "2" or aantal_bezoek == "1"):22        return True23    else:24        return False25def bezoek_korting(aantalbezoeken, score):26    if aantalbezoeken == 1:27        score /= 228    elif aantalbezoeken == 2:29        score *= 230    elif aantalbezoeken == 3:31        score *= 332    return score33def main():34    naam = input("Naam: ")35    winnaar = ""36    score = 037    random_getal = randint(0, 10000)38    som_gewonnengetal = 039    bezoek_per_maand = 040    while naam != "xxx" and naam != "qqq":41        geboortejaar = int(input("Geboortejaar: "))42        bezoek_per_maand = int(input("Hoevaak per maand bezoekt u de kinepolis? (1 = weinig, 2 = matig, 3 = veel): "))43        versnaperingen = input("Wat neemt u als versnapering? (p = popcorn, c = chips, n = niets): ")44        som = basisscore_berekenen(naam, bezoek_per_maand, geboortejaar)45        print(naam, ": ", som)46        if is_slechteklant(versnaperingen, bezoek_per_maand):47            som -= 105048        if som > score:49            winnaar = naam50            score = som51        naam = input("Naam: ")52    while random_getal < 5000 and random_getal % 10 != 0:53        if random_getal % 2 != 0:54            random_getal = randint(0, 10000)55    if winnaar != "":56        print(winnaar, ": Jij hebt gewonnen!")57        print("Jouw score is: ", bezoek_korting(bezoek_per_maand, score))58        print("Het random gegenereerde getal is: ", random_getal)59        print(winnaar, ", Jij wint hierbij", gewonnen_tickets(random_getal), "filmtickets!.")60if __name__ == '__main__':...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.