mists-polish.RdIf the proportion of overall missings is less than the cutoff,
na_polish_measures() removes columns or observations.
na_polish_key() polishes data by rows or observations, removing the whole
rows of key series.
na_polish_index() polishes data by rows or observations, removing either
the starting or the ending NA blocks (if any) within each key series.
na_polish_index2() polishes data by rows or observations, removing the
ending NA blocks (if any) within each key series. It is a shortcut of
na_polish_index(na_fun = na_ends_with).
na_polish_measures(data, cutoff) na_polish_key(data, cutoff) na_polish_index(data, cutoff, na_fun = na_starts_with) na_polish_index2(data, cutoff)
| data | A tsibble. |
|---|---|
| cutoff | A numeric between 0 and 1. Rows/cols will be kept, if the proportion of overall missings is less than the cutoff. |
| na_fun | Either |
The proportion of overall missings is defined as the number of NA divided
by the number of measurements (i.e. excluding key and index).
Other missing value polishing functions: na_polish_auto,
na_polish_metrics
wdi_ts <- tsibble::as_tsibble(wdi, key = country_code, index = year) (wdi_cols <- na_polish_measures(wdi_ts, cutoff = .7))#> # A tsibble: 10,850 x 46 [1Y] #> # Key: country_code [217] #> country_code year ag_lnd_frst_k2 ag_srf_totl_k2 bx_klt_dinv_cd_… #> <fct> <int> <dbl> <dbl> <dbl> #> 1 BDI 1969 NA 27830 NA #> 2 BDI 1970 NA 27830 NA #> 3 BDI 1971 NA 27830 NA #> 4 BDI 1972 NA 27830 NA #> 5 BDI 1973 NA 27830 NA #> 6 BDI 1974 NA 27830 NA #> 7 BDI 1975 NA 27830 NA #> 8 BDI 1976 NA 27830 NA #> 9 BDI 1977 NA 27830 NA #> 10 BDI 1978 NA 27830 NA #> # … with 10,840 more rows, and 41 more variables: bx_trf_pwkr_cd_dt <dbl>, #> # dt_dod_dect_cd <dbl>, dt_oda_alld_cd <dbl>, dt_tds_dect_ex_zs <dbl>, #> # eg_use_elec_kh_pc <dbl>, eg_use_pcap_kg_oe <dbl>, en_atm_co2e_pc <dbl>, #> # en_pop_dnst <dbl>, fs_ast_doms_gd_zs <dbl>, gc_rev_xgrt_gd_zs <dbl>, #> # gc_tax_totl_gd_zs <dbl>, it_cel_sets_p2 <dbl>, ms_mil_xpnd_gd_zs <dbl>, #> # ne_exp_gnfs_zs <dbl>, ne_gdi_totl_zs <dbl>, ne_imp_gnfs_zs <dbl>, #> # nv_agr_totl_zs <dbl>, nv_ind_totl_zs <dbl>, ny_gdp_defl_kd_zg <dbl>, #> # ny_gdp_mktp_cd <dbl>, ny_gdp_mktp_kd_zg <dbl>, ny_gnp_atls_cd <dbl>, #> # ny_gnp_mktp_pp_cd <dbl>, ny_gnp_pcap_cd <dbl>, ny_gnp_pcap_pp_cd <dbl>, #> # se_enr_prsc_fm_zs <dbl>, se_prm_cmpt_zs <dbl>, se_prm_enrr <dbl>, #> # se_sec_enrr <dbl>, sh_dyn_aids_zs <dbl>, sh_dyn_mort <dbl>, #> # sh_imm_meas <dbl>, sp_ado_tfrt <dbl>, sp_dyn_le00_in <dbl>, #> # sp_dyn_tfrt_in <dbl>, sp_pop_grow <dbl>, sp_pop_totl <dbl>, #> # sp_urb_grow <dbl>, tg_val_totl_gd_zs <dbl>, tt_pri_mrch_xd_wd <dbl>, #> # tx_val_tech_mf_zs <dbl>#> [1] "er_h2o_fwtl_zs" "er_ptd_totl_zs" "ic_reg_durs" "iq_sci_ovrl" #> [5] "sh_sta_brtc_zs" "sh_sta_maln_zs" "si_dst_frst_20" "si_pov_dday" #> [9] "si_pov_nahc" "sm_pop_netm" "sp_dyn_conu_zs"na_polish_key(wdi_ts, cutoff = .7)#> # A tsibble: 9,600 x 57 [1Y] #> # Key: country_code [192] #> country_code year ag_lnd_frst_k2 ag_srf_totl_k2 bx_klt_dinv_cd_… #> <fct> <int> <dbl> <dbl> <dbl> #> 1 BDI 1969 NA 27830 NA #> 2 BDI 1970 NA 27830 NA #> 3 BDI 1971 NA 27830 NA #> 4 BDI 1972 NA 27830 NA #> 5 BDI 1973 NA 27830 NA #> 6 BDI 1974 NA 27830 NA #> 7 BDI 1975 NA 27830 NA #> 8 BDI 1976 NA 27830 NA #> 9 BDI 1977 NA 27830 NA #> 10 BDI 1978 NA 27830 NA #> # … with 9,590 more rows, and 52 more variables: bx_trf_pwkr_cd_dt <dbl>, #> # dt_dod_dect_cd <dbl>, dt_oda_alld_cd <dbl>, dt_tds_dect_ex_zs <dbl>, #> # eg_use_elec_kh_pc <dbl>, eg_use_pcap_kg_oe <dbl>, en_atm_co2e_pc <dbl>, #> # en_pop_dnst <dbl>, er_h2o_fwtl_zs <dbl>, er_ptd_totl_zs <dbl>, #> # fs_ast_doms_gd_zs <dbl>, gc_rev_xgrt_gd_zs <dbl>, gc_tax_totl_gd_zs <dbl>, #> # ic_reg_durs <dbl>, iq_sci_ovrl <dbl>, it_cel_sets_p2 <dbl>, #> # ms_mil_xpnd_gd_zs <dbl>, ne_exp_gnfs_zs <dbl>, ne_gdi_totl_zs <dbl>, #> # ne_imp_gnfs_zs <dbl>, nv_agr_totl_zs <dbl>, nv_ind_totl_zs <dbl>, #> # ny_gdp_defl_kd_zg <dbl>, ny_gdp_mktp_cd <dbl>, ny_gdp_mktp_kd_zg <dbl>, #> # ny_gnp_atls_cd <dbl>, ny_gnp_mktp_pp_cd <dbl>, ny_gnp_pcap_cd <dbl>, #> # ny_gnp_pcap_pp_cd <dbl>, se_enr_prsc_fm_zs <dbl>, se_prm_cmpt_zs <dbl>, #> # se_prm_enrr <dbl>, se_sec_enrr <dbl>, sh_dyn_aids_zs <dbl>, #> # sh_dyn_mort <dbl>, sh_imm_meas <dbl>, sh_sta_brtc_zs <dbl>, #> # sh_sta_maln_zs <dbl>, si_dst_frst_20 <dbl>, si_pov_dday <dbl>, #> # si_pov_nahc <dbl>, sm_pop_netm <dbl>, sp_ado_tfrt <dbl>, #> # sp_dyn_conu_zs <dbl>, sp_dyn_le00_in <dbl>, sp_dyn_tfrt_in <dbl>, #> # sp_pop_grow <dbl>, sp_pop_totl <dbl>, sp_urb_grow <dbl>, #> # tg_val_totl_gd_zs <dbl>, tt_pri_mrch_xd_wd <dbl>, tx_val_tech_mf_zs <dbl>na_polish_index(wdi_ts, cutoff = .7)#> # A tsibble: 6,876 x 57 [1Y] #> # Key: country_code [197] #> country_code year ag_lnd_frst_k2 ag_srf_totl_k2 bx_klt_dinv_cd_… #> <fct> <int> <dbl> <dbl> <dbl> #> 1 BDI 1980 NA 27830 NA #> 2 BDI 1981 NA 27830 NA #> 3 BDI 1982 NA 27830 NA #> 4 BDI 1983 NA 27830 NA #> 5 BDI 1984 NA 27830 NA #> 6 BDI 1985 NA 27830 538567. #> 7 BDI 1986 NA 27830 1524029. #> 8 BDI 1987 NA 27830 1367714. #> 9 BDI 1988 NA 27830 1196624. #> 10 BDI 1989 NA 27830 567227. #> # … with 6,866 more rows, and 52 more variables: bx_trf_pwkr_cd_dt <dbl>, #> # dt_dod_dect_cd <dbl>, dt_oda_alld_cd <dbl>, dt_tds_dect_ex_zs <dbl>, #> # eg_use_elec_kh_pc <dbl>, eg_use_pcap_kg_oe <dbl>, en_atm_co2e_pc <dbl>, #> # en_pop_dnst <dbl>, er_h2o_fwtl_zs <dbl>, er_ptd_totl_zs <dbl>, #> # fs_ast_doms_gd_zs <dbl>, gc_rev_xgrt_gd_zs <dbl>, gc_tax_totl_gd_zs <dbl>, #> # ic_reg_durs <dbl>, iq_sci_ovrl <dbl>, it_cel_sets_p2 <dbl>, #> # ms_mil_xpnd_gd_zs <dbl>, ne_exp_gnfs_zs <dbl>, ne_gdi_totl_zs <dbl>, #> # ne_imp_gnfs_zs <dbl>, nv_agr_totl_zs <dbl>, nv_ind_totl_zs <dbl>, #> # ny_gdp_defl_kd_zg <dbl>, ny_gdp_mktp_cd <dbl>, ny_gdp_mktp_kd_zg <dbl>, #> # ny_gnp_atls_cd <dbl>, ny_gnp_mktp_pp_cd <dbl>, ny_gnp_pcap_cd <dbl>, #> # ny_gnp_pcap_pp_cd <dbl>, se_enr_prsc_fm_zs <dbl>, se_prm_cmpt_zs <dbl>, #> # se_prm_enrr <dbl>, se_sec_enrr <dbl>, sh_dyn_aids_zs <dbl>, #> # sh_dyn_mort <dbl>, sh_imm_meas <dbl>, sh_sta_brtc_zs <dbl>, #> # sh_sta_maln_zs <dbl>, si_dst_frst_20 <dbl>, si_pov_dday <dbl>, #> # si_pov_nahc <dbl>, sm_pop_netm <dbl>, sp_ado_tfrt <dbl>, #> # sp_dyn_conu_zs <dbl>, sp_dyn_le00_in <dbl>, sp_dyn_tfrt_in <dbl>, #> # sp_pop_grow <dbl>, sp_pop_totl <dbl>, sp_urb_grow <dbl>, #> # tg_val_totl_gd_zs <dbl>, tt_pri_mrch_xd_wd <dbl>, tx_val_tech_mf_zs <dbl>na_polish_index2(wdi_ts, cutoff = .7)#> # A tsibble: 8,997 x 57 [1Y] #> # Key: country_code [210] #> country_code year ag_lnd_frst_k2 ag_srf_totl_k2 bx_klt_dinv_cd_… #> <fct> <int> <dbl> <dbl> <dbl> #> 1 BDI 1969 NA 27830 NA #> 2 BDI 1970 NA 27830 NA #> 3 BDI 1971 NA 27830 NA #> 4 BDI 1972 NA 27830 NA #> 5 BDI 1973 NA 27830 NA #> 6 BDI 1974 NA 27830 NA #> 7 BDI 1975 NA 27830 NA #> 8 BDI 1976 NA 27830 NA #> 9 BDI 1977 NA 27830 NA #> 10 BDI 1978 NA 27830 NA #> # … with 8,987 more rows, and 52 more variables: bx_trf_pwkr_cd_dt <dbl>, #> # dt_dod_dect_cd <dbl>, dt_oda_alld_cd <dbl>, dt_tds_dect_ex_zs <dbl>, #> # eg_use_elec_kh_pc <dbl>, eg_use_pcap_kg_oe <dbl>, en_atm_co2e_pc <dbl>, #> # en_pop_dnst <dbl>, er_h2o_fwtl_zs <dbl>, er_ptd_totl_zs <dbl>, #> # fs_ast_doms_gd_zs <dbl>, gc_rev_xgrt_gd_zs <dbl>, gc_tax_totl_gd_zs <dbl>, #> # ic_reg_durs <dbl>, iq_sci_ovrl <dbl>, it_cel_sets_p2 <dbl>, #> # ms_mil_xpnd_gd_zs <dbl>, ne_exp_gnfs_zs <dbl>, ne_gdi_totl_zs <dbl>, #> # ne_imp_gnfs_zs <dbl>, nv_agr_totl_zs <dbl>, nv_ind_totl_zs <dbl>, #> # ny_gdp_defl_kd_zg <dbl>, ny_gdp_mktp_cd <dbl>, ny_gdp_mktp_kd_zg <dbl>, #> # ny_gnp_atls_cd <dbl>, ny_gnp_mktp_pp_cd <dbl>, ny_gnp_pcap_cd <dbl>, #> # ny_gnp_pcap_pp_cd <dbl>, se_enr_prsc_fm_zs <dbl>, se_prm_cmpt_zs <dbl>, #> # se_prm_enrr <dbl>, se_sec_enrr <dbl>, sh_dyn_aids_zs <dbl>, #> # sh_dyn_mort <dbl>, sh_imm_meas <dbl>, sh_sta_brtc_zs <dbl>, #> # sh_sta_maln_zs <dbl>, si_dst_frst_20 <dbl>, si_pov_dday <dbl>, #> # si_pov_nahc <dbl>, sm_pop_netm <dbl>, sp_ado_tfrt <dbl>, #> # sp_dyn_conu_zs <dbl>, sp_dyn_le00_in <dbl>, sp_dyn_tfrt_in <dbl>, #> # sp_pop_grow <dbl>, sp_pop_totl <dbl>, sp_urb_grow <dbl>, #> # tg_val_totl_gd_zs <dbl>, tt_pri_mrch_xd_wd <dbl>, tx_val_tech_mf_zs <dbl>