stimmenfryslan/notebooks/Create dataset for Voice Sauce.ipynb

In [1]:

from glob import glob
from os import listdir, symlink
import pandas

from collections import Counter

import MySQLdb
db = MySQLdb.connect(user='root', passwd='Nmmxhjgt1@', db='stimmenfryslan')

In [2]:

source = '/media/herbert/Herbert Kruitbos/Data Sets/Stimmen Fryslan 2018-06026/picture_game_recordings/'
destination = '/media/herbert/Herbert Kruitbos/Data Sets/Stimmen Fryslan 2018-06026/picture_game_recordings_for_voice_sauce/'

In [3]:

filenames = [
    filename
    for filename in glob(source + '*/*/*.wav')
    if any(
        filename.split('/')[-1].startswith('pg_' + word + '_')
        for word in {'ei', 'meeuw', 'maan', 'molen', 'mond', 'nagel', 'uil'}
    )
]

In [4]:

# for filename in filenames:
#     symlink(
#         '../picture_game_recordings/' + filename[len(source):],
#         destination + filename.split('/')[-1]
#     )

In [5]:

Counter(filename.split('/')[-3] for filename in filenames)
None

In [6]:

# left_over = pandas.read_csv('left_over/output.txt', sep='\t')
# left_over['A2c'] = [
#     x if type(x) == float else (
#         0 if x == '-' else float(x)
#     ) for x in left_over['A2c']
# ]

# left_over.drop(columns=[c for c in left_over.columns if c.startswith('Unnamed: ')], inplace=True)
# left_over = left_over.groupby(['Filename']).agg({
#     field: aggregations
#     for aggregations, fields in [
#         (['max'], ['t_ms']),
#         (['mean', 'std'],
#          ['H1c', 'H2c', 'H4c', 'A1c', 'A2c', 'A3c', 'H2Kc',
#           'H1H2c', 'H2H4c', 'H1A1c', 'H1A2c', 'H1A3c', 'H42Kc', 'H2KH5Kc', 'CPP',
#           'Energy', 'HNR05', 'HNR15', 'HNR25', 'HNR35', 'SHR', 'H1u', 'H2u',
#           'H4u', 'A1u', 'A2u', 'A3u', 'H2Ku', 'H5Ku', 'H1H2u', 'H2H4u', 'H1A1u',
#           'H1A2u', 'H1A3u', 'H42Ku', 'H2KH5Ku', 'strF0', 'sF0', 'pF0', 'shrF0',
#           'oF0', 'sF1', 'sF2', 'sF3', 'sF4', 'pF1', 'pF2', 'pF3', 'pF4', 'oF1',
#           'oF2', 'oF3', 'oF4', 'sB1', 'sB2', 'sB3', 'sB4', 'pB1', 'pB2', 'pB3',
#           'pB4', 'oB1', 'oB2', 'oB3', 'oB4', 'epoch', 'soe']),
#     ]
#     for field in fields
# })
# left_over.reset_index(drop=False, inplace=True)
# left_over['Filename'] = [filename[:-3] + 'wav' for filename in left_over['Filename']]

# parameters = pandas.concat([parameters, left_over])

In [7]:

sheets = []
for f in glob('voicesauce_output/*.txt') + ['left_over/output.txt']:
    parameters = pandas.read_csv(f, sep='\t')
    parameters['A2c'] = [
        x if type(x) == float else (
            0 if x == '-' else float(x)
        ) for x in parameters['A2c']
    ]
    parameters.drop(columns=[c for c in parameters.columns if c.startswith('Unnamed: ')], inplace=True)
    parameters = parameters.groupby(['Filename']).agg({
        field: aggregations
        for aggregations, fields in [
            (['max'], ['t_ms']),
            (['mean', 'std'],
             ['H1c', 'H2c', 'H4c', 'A1c', 'A2c', 'A3c', 'H2Kc',
              'H1H2c', 'H2H4c', 'H1A1c', 'H1A2c', 'H1A3c', 'H42Kc', 'H2KH5Kc', 'CPP',
              'Energy', 'HNR05', 'HNR15', 'HNR25', 'HNR35', 'SHR', 'H1u', 'H2u',
              'H4u', 'A1u', 'A2u', 'A3u', 'H2Ku', 'H5Ku', 'H1H2u', 'H2H4u', 'H1A1u',
              'H1A2u', 'H1A3u', 'H42Ku', 'H2KH5Ku', 'strF0', 'sF0', 'pF0', 'shrF0',
              'oF0', 'sF1', 'sF2', 'sF3', 'sF4', 'pF1', 'pF2', 'pF3', 'pF4', 'oF1',
              'oF2', 'oF3', 'oF4', 'sB1', 'sB2', 'sB3', 'sB4', 'pB1', 'pB2', 'pB3',
              'pB4', 'oB1', 'oB2', 'oB3', 'oB4', 'epoch', 'soe']),
        ]
        for field in fields
    })
    sheets.append(parameters)

parameters = pandas.concat(sheets)
parameters.reset_index(drop=False, inplace=True)
parameters['Filename'] = [filename[:-3] + 'wav' for filename in parameters['Filename']]

/home/herbert/.virtualenvs/stimmenfryslan/lib/python3.5/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (9) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

In [16]:

parameters.reset_index(drop=False, inplace=True)

In [29]:

# SELECT user_lat, user_lng, question_text, answer_text
games = pandas.read_sql('''
SELECT language.name as language, item.name as picture,
       survey.user_lat as latitude, survey.user_lng as longitude,
       survey.area_name as area, survey.country_name as country,
       result.recording as filename,
       result.submitted_at as date
FROM       core_surveyresult as survey
INNER JOIN core_picturegameresult as result ON survey.id = result.survey_result_id
INNER JOIN core_language as language ON language.id = result.language_id
INNER JOIN core_picturegameitem as item
    ON result.picture_game_item_id = item.id
''', db)
games['filename'] = [filename.split('/')[-1] for filename in games['filename']]
games = games.set_index('filename')

In [30]:

games_aggregated = games.groupby('filename').aggregate(['first'])

In [27]:

joined = parameters.join(games_aggregated, on='Filename', how='left')

In [31]:

joined

Out[31]:

	Filename	Energy		H1A1u		epoch		H4c		sB4	...	oB2	H1A2c		language	picture	latitude	longitude	area	country	date
		mean	std	mean	std	mean	std	mean	std	mean	...	std	mean	std	first	first	first	first	first	first	first
0	pg_ei_1479_w6ocz.wav	0.006093	0.010032	-8.363866	8.362089	0.088705	0.284408	-24.249126	14.070339	501.476549	...	0.0	12.996846	9.540718	Frysk	Ei	52.852931	5.513851	Oudemirdum	Netherlands	2017-09-20 20:37:43
1	pg_ei_147_jqofa.wav	14.528631	20.464746	-19.329911	7.900788	0.198810	0.399342	1.035145	15.152155	389.587995	...	0.0	6.938438	5.955710	Nederlands	Ei	53.243626	6.144059	Buitenpost	Netherlands	2017-07-05 08:26:15
2	pg_ei_1490_s2lwa.wav	1.848744	4.192697	15.298327	17.760301	0.048753	0.215412	-8.390735	14.680598	426.391044	...	0.0	40.548968	18.726303	Frysk	Ei	53.255520	6.035780	De Westereen	Netherlands	2017-09-20 20:29:52
3	pg_ei_1492_awq4v.wav	1.519375	4.940569	12.590643	6.722463	0.050523	0.219072	-23.054530	13.048955	443.566868	...	0.0	35.335184	10.494196	Nederlands	Ei	52.206159	5.970381	Apeldoorn	Netherlands	2017-09-20 20:29:21
4	pg_ei_1498_qo2f4.wav	2.115565	5.390331	3.790873	6.826134	0.061936	0.241089	-16.374206	15.838637	447.941753	...	0.0	28.641463	9.832852	Stadsfrys	Ei	53.445709	5.773903	Nes	Netherlands	2017-09-20 21:04:14
5	pg_ei_1505_rc6fv.wav	0.485461	1.476672	-2.100762	8.216539	0.131000	0.337477	-28.594425	19.684338	466.455555	...	0.0	17.555613	7.521186	Frysk	Ei	53.203072	5.797008	Leeuwarden	Netherlands	2017-09-20 20:36:34
6	pg_ei_152_vg2ni.wav	0.958645	1.520238	-6.613446	10.624312	0.178213	0.382779	-7.416307	7.437012	378.929968	...	0.0	16.660822	10.215175	Deutsch	Ei	53.280726	6.147990	Kollum	Netherlands	2017-07-05 08:26:28
7	pg_ei_1532_z0dsl.wav	3.288982	5.083560	-0.829085	7.790741	0.257692	0.437532	-18.974677	24.308963	487.564188	...	0.0	12.191213	8.287945	Frysk	Ei	53.373507	5.966474	Ternaard	Netherlands	2017-09-21 17:17:26
8	pg_ei_1533_hqc0r.wav	1.796025	5.255063	8.457886	9.862231	0.065057	0.246661	-9.952210	12.483633	503.026949	...	0.0	17.830095	13.087170	Frysk	Ei	53.003131	5.962632	Gersloot	Netherlands	2017-09-20 21:01:16
9	pg_ei_154_7ba6w.wav	0.399040	0.599270	-15.696802	12.624528	0.281746	0.450029	-11.536317	10.729714	308.087244	...	0.0	4.868224	6.181064	Frysk	Ei	53.251887	6.150180	Buitenpost	Netherlands	2017-07-05 08:27:23
10	pg_ei_1554_68mr7.wav	10.414797	23.115259	-1.156699	11.868009	0.138122	0.345114	-18.846513	24.444712	422.933652	...	0.0	18.769927	7.746649	Frysk	Ei	53.123229	6.103189	Drachten	Netherlands	2017-09-20 21:34:30
11	pg_ei_1578_l9f7a.wav	3.571768	8.638621	0.396819	6.376619	0.127603	0.333711	-25.244973	18.528859	408.394730	...	0.0	17.302953	7.030099	Frysk	Ei	53.097390	6.157000	Ureterp	Netherlands	2017-09-20 21:25:38
12	pg_ei_1579_4k9ry.wav	3.021018	8.622227	9.946554	10.294977	0.060051	0.237620	-9.251892	8.024785	465.112936	...	0.0	34.591340	12.677235	Frysk	Ei	53.148597	5.893380	Warten	Netherlands	2017-09-20 21:26:42
13	pg_ei_1607_rfmaq.wav	0.336351	1.192991	-2.948125	6.610633	0.118361	0.323102	-34.821794	19.096402	479.212374	...	0.0	17.649702	6.502548	Frysk	Ei	53.243142	5.893027	Gytsjerk	Netherlands	2017-09-20 22:18:46
14	pg_ei_1610_njpag.wav	0.143424	0.282195	-2.152259	7.374509	0.152603	0.359712	-35.091165	23.882210	422.934242	...	0.0	17.231031	6.349066	Frysk	Ei	53.182294	6.166471	Surhuisterveen	Netherlands	2017-09-20 22:25:44
15	pg_ei_1618_ovshb.wav	2.558292	6.390083	6.196505	9.946098	0.058599	0.234908	-14.074589	12.399100	470.875862	...	0.0	28.736906	13.433661	Bildts	Ei	53.274811	5.659052	Sint Annaparochie	Netherlands	2017-09-25 22:38:01
16	pg_ei_1633_o1veb.wav	0.150418	0.776917	-13.997056	9.858770	0.107626	0.309923	-15.760478	7.216331	499.035228	...	0.0	20.695977	6.030095	Frysk	Ei	52.881602	5.830102	Delfstrahuizen	Netherlands	2017-11-02 07:24:28
17	pg_ei_163_1lsft.wav	6.323439	11.797167	-14.739278	7.655092	0.233367	0.423080	-4.973145	16.565988	383.102945	...	0.0	8.971550	7.067476	Nederlands	Ei	53.318882	6.007953	Dokkum	Netherlands	2017-07-05 08:21:47
18	pg_ei_1656_uzrp4.wav	8.466685	14.659454	14.374309	17.269044	0.048639	0.215175	-3.184506	13.528168	422.172306	...	0.0	38.091907	18.376240	Frysk	Ei	53.209877	5.729580	Marsum	Netherlands	2017-09-21 06:26:43
19	pg_ei_1684_wy32c.wav	0.096580	0.261895	-5.267619	8.452685	0.109312	0.312100	-28.122597	13.693092	416.887486	...	0.0	12.594799	8.192683	Frysk	Ei	53.251394	6.144553	Buitenpost	Netherlands	2017-09-21 07:40:40
20	pg_ei_1709_3mapl.wav	0.313399	0.981581	6.973205	5.589335	0.132208	0.338776	-42.511799	23.762206	745.731104	...	0.0	24.035236	10.641747	Frysk	Ei	53.255131	6.144419	Buitenpost	Netherlands	2017-09-21 08:23:50
21	pg_ei_170_3d7bl.wav	0.818965	1.496516	-1.118491	6.793104	0.209375	0.406953	-12.238893	12.699559	413.199215	...	0.0	16.688808	7.849260	Frysk	Ei	53.204737	6.177682	Surhuizum	Netherlands	2017-07-05 08:25:10
22	pg_ei_1718_wbk8f.wav	2.195919	6.080640	-5.477264	6.817871	0.090093	0.286359	-23.633220	15.388735	447.298659	...	0.0	13.289985	8.388136	Frysk	Ei	53.097637	5.587097	Wommels	Netherlands	2017-09-21 08:36:27
23	pg_ei_1728_o5nfs.wav	4.632836	8.280038	-2.327510	7.041617	0.147059	0.354286	-19.732114	23.290246	600.514163	...	0.0	18.047249	8.602000	Frysk	Ei	53.081281	6.044364	Boornbergum	Netherlands	2017-09-21 09:01:16
24	pg_ei_1753_3ydgt.wav	1.924188	3.591438	5.916330	10.088331	0.112435	0.316018	-18.502797	15.620109	358.812441	...	0.0	27.283065	11.076286	Frysk	Ei	52.882571	5.403751	Warns	Netherlands	2017-09-21 09:37:10
25	pg_ei_1760_1xhdy.wav	1.019632	2.883529	-9.413395	5.949749	0.162144	0.368645	-21.279387	12.851721	438.978338	...	0.0	13.561789	6.254704	Frysk	Ei	53.147628	5.744943	Weidum	Netherlands	2017-09-21 09:44:01
26	pg_ei_1767_ycs6j.wav	1.790412	3.232086	19.764376	11.107679	0.042542	0.201875	-6.151115	6.154925	343.734384	...	0.0	38.967005	14.553001	Frysk	Ei	53.107440	6.112634	Drachten	Netherlands	2017-09-21 10:11:51
27	pg_ei_1771_oxlp4.wav	0.797014	1.865066	9.884880	9.840505	0.069993	0.255230	-16.590268	14.077787	428.609902	...	0.0	32.836338	11.926544	Stadsfrys	Ei	52.885028	5.357552	Stavoren	Netherlands	2017-09-21 10:05:19
28	pg_ei_1780_2apos.wav	4.209224	11.736406	0.654883	5.967860	0.074703	0.262967	-19.097371	17.133383	496.547349	...	0.0	23.713805	11.044562	Bildts	Ei	53.273128	5.607608	Sint Jacobiparochie	Netherlands	2017-09-22 11:36:39
29	pg_ei_1783_y6j1l.wav	4.176013	7.898707	11.995828	13.005395	0.059642	0.236901	-8.006870	12.870469	395.229482	...	0.0	34.880502	13.641485	Frysk	Ei	52.943364	5.628292	Woudsend	Netherlands	2017-09-21 11:10:34
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3604	pg_mond_7558_u5yk7.wav	0.253089	1.129148	13.279675	9.040864	0.050030	0.218018	-24.686031	11.302592	490.190664	...	0.0	38.014120	11.179564	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3605	pg_mond_7562_ueiq8.wav	0.124959	0.390776	-4.764390	7.235432	0.142625	0.349761	-26.972236	14.901011	472.516343	...	0.0	12.495093	6.212972	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3606	pg_mond_7565_x30tw.wav	0.710514	5.168457	4.243849	6.062041	0.092596	0.289881	-33.794772	13.507857	515.225966	...	0.0	26.357062	7.908492	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3607	pg_mond_7574_th70g.wav	0.613170	0.792948	1.457276	4.404910	0.178977	0.383515	-7.409416	14.482713	391.409108	...	0.0	14.298890	8.876324	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3608	pg_mond_7590_eg6fj.wav	0.080419	0.248321	-5.826644	6.359726	0.171372	0.376868	-41.740269	22.376711	388.221126	...	0.0	9.292176	8.100504	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3609	pg_mond_7612_ozhis.wav	0.051657	0.189400	2.032265	6.961066	0.137143	0.344074	-39.504976	18.617572	418.058782	...	0.0	20.184651	9.402860	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3610	pg_mond_764_wnvjl.wav	1.390605	3.227143	0.791462	7.444036	0.137429	0.344408	-21.492851	22.668333	491.530560	...	0.0	19.175367	8.050513	Frysk	Mond	53.261454	6.069029	Kollumerzwaag	Netherlands	2017-09-20 13:48:15
3611	pg_mond_7660_kt7fn.wav	0.203666	1.082149	13.199955	7.345656	0.073728	0.261342	-32.373095	11.863870	426.344791	...	0.0	38.819690	11.687076	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3612	pg_mond_7688_nghm6.wav	0.944088	3.836126	-8.009504	9.505854	0.138938	0.345933	-23.021969	17.587367	435.896839	...	0.0	12.628905	9.396618	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3613	pg_mond_7704_brjtl.wav	0.952383	3.283208	2.934111	7.591404	0.081564	0.273765	-32.565145	22.409171	651.791112	...	0.0	22.575932	9.874725	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3614	pg_mond_771_m9wd2.wav	0.357439	1.170794	1.444918	7.224172	0.095221	0.293573	-33.098590	18.996865	748.994114	...	0.0	18.814434	7.039397	Frysk	Mond	53.187913	6.130642	Harkema	Netherlands	2017-09-20 14:02:40
3615	pg_mond_7753_ekiz1.wav	0.195193	0.385663	2.590834	5.616180	0.180730	0.384910	-29.128703	22.527613	496.672836	...	0.0	20.452346	9.348115	NaN	NaN	NaN	NaN	NaN	NaN	NaT
3616	pg_mond_779_9lhb4.wav	0.270411	1.443022	4.642808	3.817853	0.072625	0.259532	-28.609838	9.913971	486.522804	...	0.0	26.144631	6.930861	Frysk	Mond	53.238427	5.993419	Feanwâlden	Netherlands	2017-09-20 17:04:26
3617	pg_mond_77_r0mw5.wav	12.615063	14.230695	-2.168674	6.853561	0.241211	0.427922	0.790852	18.177054	354.465754	...	0.0	16.373549	7.392439	Frysk	Mond	53.242708	6.199835	Gerkesklooster	Netherlands	2017-07-05 06:40:15
3618	pg_mond_795_kpn9a.wav	0.164596	0.636454	1.260164	6.633398	0.072761	0.259756	-7.345207	8.348875	527.210449	...	0.0	25.233131	6.674325	Frysk	Mond	52.926116	5.739020	Sint Nicolaasga	Netherlands	2017-09-20 14:24:58
3619	pg_mond_79_k2oby.wav	4.051959	8.274621	-1.949634	7.056929	0.220833	0.414916	-5.345144	12.854728	281.995092	...	0.0	14.915587	10.393552	Frysk	Mond	53.174947	6.057054	Eastermar	Netherlands	2017-07-05 06:48:48
3620	pg_mond_851_zgdv6.wav	0.187804	0.440421	-1.327140	7.820476	0.120932	0.326100	-28.506043	17.497266	465.653998	...	0.0	18.322024	7.841020	Frysk	Mond	53.337666	5.824662	Ferwert	Netherlands	2017-09-20 15:25:10
3621	pg_mond_85_uw0ck.wav	0.544519	1.318256	-11.131253	7.474641	0.152936	0.360011	-15.227187	15.900314	399.210000	...	0.0	12.575625	8.050369	Frysk	Mond	53.235113	6.094181	Twijzel	Netherlands	2017-07-05 06:47:13
3622	pg_mond_86_0jp3y.wav	0.202151	0.347113	-5.096460	7.446010	0.247768	0.431837	-17.635790	17.131390	400.472476	...	0.0	15.644899	7.891115	Frysk	Mond	53.184433	6.174556	Surhuisterveen	Netherlands	2017-07-05 06:49:03
3623	pg_mond_888_72kyf.wav	2.144732	5.252261	-2.598460	7.809499	0.178231	0.382794	-23.726831	20.087603	473.367444	...	0.0	19.739390	7.958076	Frysk	Mond	53.276534	5.663216	Sint Annaparochie	Netherlands	2017-09-20 15:57:44
3624	pg_mond_89_h8ydq.wav	3.430183	6.185558	-8.763739	9.042689	0.121489	0.326747	0.611966	9.890541	444.943951	...	0.0	14.812221	8.637573	Frysk	Mond	53.197942	6.114447	Drogeham	Netherlands	2017-07-05 06:47:18
3625	pg_mond_915_ynko1.wav	4.249877	9.045231	2.554132	9.423918	0.077660	0.267703	-15.489450	22.467622	347.358984	...	0.0	24.982211	10.150435	Frysk	Mond	52.850864	5.699769	Lemmer	Netherlands	2017-09-20 16:34:57
3626	pg_mond_955_unt9j.wav	0.166611	0.447291	6.292969	6.486585	0.073555	0.261082	-18.711667	10.412328	429.887114	...	0.0	30.979489	8.059298	Frysk	Mond	52.959922	5.920814	Heerenveen	Netherlands	2017-09-20 16:28:10
3627	pg_mond_95_jux7b.wav	3.464729	4.763932	-3.103434	8.282137	0.223090	0.416499	-2.509244	18.551318	401.115338	...	0.0	12.029864	9.413974	Frysk	Mond	53.260363	6.082873	Kollumerzwaag	Netherlands	2017-07-05 07:31:57
3628	pg_mond_967_ia47p.wav	5.916577	10.767338	3.334500	7.138865	0.088597	0.284278	-15.354755	19.645089	408.198314	...	0.0	30.645523	10.466913	Frysk	Mond	53.274088	5.996400	Broeksterwald	Netherlands	2017-09-20 16:29:10
3629	pg_mond_97_rjukn.wav	11.212797	18.435150	-6.524169	10.242092	0.168087	0.374032	-0.801914	16.137070	372.319386	...	0.0	13.862854	7.236919	Frysk	Mond	53.252962	6.150368	Buitenpost	Netherlands	2017-07-05 07:29:46
3630	pg_mond_981_e4gm9.wav	0.326556	1.830656	-3.553581	9.515012	0.236232	0.424788	-32.843768	14.675817	393.698786	...	0.0	15.936397	10.445577	Frysk	Mond	53.181382	6.107598	Harkema	Netherlands	2017-09-20 16:34:23
3631	pg_mond_984_dbmq8.wav	0.480206	2.569899	12.741191	6.714312	0.068590	0.252768	-18.150326	8.231644	506.418191	...	0.0	41.256388	8.679365	Frysk	Mond	53.219545	5.791209	Leeuwarden	Netherlands	2017-09-20 16:36:46
3632	pg_mond_985_ojkqg.wav	1.464015	7.068337	2.489865	5.506252	0.057091	0.232028	-13.999746	12.301611	487.082574	...	0.0	37.246930	9.055718	Frysk	Mond	53.239486	5.998377	Feanwâlden	Netherlands	2017-09-20 16:41:22
3633	pg_mond_99_ofu5p.wav	4.246389	5.959799	-6.657253	7.377999	0.251078	0.433691	-4.289402	13.449593	364.211929	...	0.0	11.170874	9.327788	Frysk	Mond	53.213373	6.061058	Jistrum	Netherlands	2017-07-05 07:35:08

3634 rows × 143 columns

In [32]:

expected_files = [
    f.split('/')[-1]
    for f in glob(
        '/media/herbert/Herbert Kruitbos/Data Sets/Stimmen Fryslan 2018-06026/picture_game_recordings_for_voice_sauce/pg_*.wav')
]
# ','.join(f[:-3] + 'mat' for f in set(expected_files) - set(parameters['Filename']))

set(expected_files) - set(parameters['Filename'])

Out[32]:

{'pg_ei_2862_lr9qm.wav',
 'pg_maan_6266_a6w93.wav',
 'pg_meeuw_485_2rnjh.wav',
 'pg_meeuw_5945_35eyh.wav',
 'pg_meeuw_999_geulp.wav',
 'pg_molen_6659_7jcf6.wav',
 'pg_mond_2795_dy2ot.wav',
 'pg_mond_2862_8urpy.wav',
 'pg_nagel_1060_gmnzf.wav',
 'pg_nagel_2862_yj61v.wav',
 'pg_uil_1967_jtfcp.wav'}

In [33]:

joined.to_excel('/home/herbert/Stimmen_VoiceSauce_all_2_headers.xls')