notebook.community

Edit and run



In [40]:

    
library(dplyr)



In [41]:

    
quality_prediction_and_page_views <- read.table("../results/sql_queries/entity_views_and_aggregated_revisions/entity_views_and_aggregated_revisions_and_quality_scoring_correlation.tsv", header=FALSE, sep="\t")



In [42]:

    
colnames(quality_prediction_and_page_views) <- c('yymm','spearman_corr_of_views_versus_quality', 'p')



In [43]:

    
monthly_bot_edits <- read.table("../results/wikidata_page_revisions_with_timestamp_bot_info/monthly_bot_edits_converted.tsv", header=FALSE, sep="\t")



In [44]:

    
colnames(monthly_bot_edits) <- c('yyyy','mm', 'yymm', 'prev_month_bot_edits_over_total', 'prev_month_bot_edits', 'prev_month_edits')



In [45]:

    
quality_predictions_and_page_views_and_monthly_bot_edits <- merge(monthly_bot_edits, quality_prediction_and_page_views, by='yymm')[c('yymm','prev_month_bot_edits_over_total', 'prev_month_bot_edits', 'prev_month_edits', 'spearman_corr_of_views_versus_quality', 'p')]



In [46]:

    
sorted_quality_prediction_and_page_views <- dplyr::arrange(quality_prediction_and_page_views, yymm)



In [47]:

    
sorted_quality_predictions_and_page_views_and_monthly_bot_edits <- dplyr::arrange(quality_predictions_and_page_views_and_monthly_bot_edits, yymm)



In [48]:

    
sorted_quality_prediction_and_page_views$row_number <- matrix(1:57,57,1)



In [49]:

    
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number <- matrix(1:56,56,1)



In [50]:

    
head(sorted_quality_predictions_and_page_views_and_monthly_bot_edits, n=60)









    





yymm prev_month_bot_edits_over_total prev_month_bot_edits prev_month_edits spearman_corr_of_views_versus_quality p row_number

	1211         0.002649431       703       265340     0.40610964   4.559667e-174  1           
	1212         0.439382794    183981       418726     0.16410131    0.000000e+00  2           
	1301         0.907962344   1949811      2147458     0.09222488    0.000000e+00  3           
	1302         0.922694936   2337846      2533715     0.14043395    0.000000e+00  4           
	1303         0.862359141   2327478      2698966     0.17557653    0.000000e+00  5           
	1304         0.903903559   8256322      9134074     0.22929523    0.000000e+00  6           
	1305         0.948170642  13900943     14660803     0.23063940    0.000000e+00  7           
	1306         0.940258291  14463573     15382553     0.25586321    0.000000e+00  8           
	1307         0.817919933   3850902      4708165     0.25671401    0.000000e+00  9           
	1308         0.918788902   8355311      9093831     0.26641139    0.000000e+00 10           
	1309         0.836895853   4091547      4888956     0.27332548    0.000000e+00 11           
	1310         0.869537443   5150692      5923485     0.27802750    0.000000e+00 12           
	1311         0.938626146   8500770      9056609     0.26782685    0.000000e+00 13           
	1312         0.883819379   6840625      7739845     0.25963683    0.000000e+00 14           
	1401         0.873717052   5688500      6510689     0.26579848    0.000000e+00 15           
	1402         0.905460154   8359698      9232541     0.27391589    0.000000e+00 16           
	1403         0.854197858   5062952      5927142     0.27164557    0.000000e+00 17           
	1404         0.867425753   4839056      5578640     0.20208494    0.000000e+00 18           
	1405         0.807545341   4412498      5464087     0.20141655    0.000000e+00 19           
	1406         0.854548731   9606783     11241937     0.17606298    0.000000e+00 20           
	1407         0.710971257   4310040      6062186     0.16898030    0.000000e+00 21           
	1408         0.657433561   4395942      6686519     0.15423070    0.000000e+00 22           
	1409         0.684800157   4053302      5918956     0.09475239    0.000000e+00 23           
	1410         0.679908395   4089341      6014547     0.05780762    0.000000e+00 24           
	1411         0.762452031   6653100      8725926     0.05964949    0.000000e+00 25           
	1412         0.809998497   6835681      8439128     0.04531066    0.000000e+00 26           
	1501         0.734080536   4978278      6781651     0.04630314    0.000000e+00 27           
	1502         0.749753801   5460241      7282712     0.09211579    0.000000e+00 28           
	1503         0.719331520   5341225      7425262     0.13049032    0.000000e+00 29           
	1504         0.778160065   6195498      7961727     0.13480227    0.000000e+00 30           
	1505         0.539082365   2914048      5405571     0.12512988    0.000000e+00 31           
	1506         0.730264168   5227607      7158515     0.11263627    0.000000e+00 32           
	1507         0.625321026   2866556      4584135     0.12586697    0.000000e+00 33           
	1508         0.878790677  11048877     12572820     0.06287843    0.000000e+00 34           
	1509         0.766204690   6627289      8649502     0.04692934    0.000000e+00 35           
	1510         0.741281404   5444726      7345019     0.04452854    0.000000e+00 36           
	1511         0.758349532   9315279     12283622     0.06394301    0.000000e+00 37           
	1512         0.677263809   7509707     11088304     0.06209993    0.000000e+00 38           
	1601         0.562167380   5350179      9517057     0.07764267    0.000000e+00 39           
	1602         0.540641446   5821280     10767358     0.09725208    0.000000e+00 40           
	1603         0.564259837   5680814     10067727     0.12001179    0.000000e+00 41           
	1604         0.554568941   4977396      8975252     0.12304755    0.000000e+00 42           
	1605         0.685493608   7032518     10259057     0.11738700    0.000000e+00 43           
	1606         0.725654544  10163437     14005889     0.11620185    0.000000e+00 44           
	1607         0.373705914   3919175     10487324     0.11903759    0.000000e+00 45           
	1608         0.572841083   4722664      8244283     0.14158668    0.000000e+00 46           
	1609         0.576158200   6172895     10713889     0.14027799    0.000000e+00 47           
	1610         0.329518100   3566783     10824240     0.14939584    0.000000e+00 48           
	1611         0.606654432   9851141     16238472     0.15221274    0.000000e+00 49           
	1612         0.613149457   8333936     13592014     0.15849012    0.000000e+00 50           
	1701         0.438299035   4478927     10218884     0.15245836    0.000000e+00 51           
	1702         0.465745975   7963334     17098020     0.15399518    0.000000e+00 52           
	1703         0.639370516  11542070     18052240     0.13894629    0.000000e+00 53           
	1704         0.631230587   8202274     12994101     0.14494673    0.000000e+00 54           
	1705         0.623490165   5456289      8751203     0.13676837    0.000000e+00 55           
	1706         0.572228020    121171       211753     0.13588080    0.000000e+00 56



In [51]:

    
plot(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number, sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality, xlab="Month", ylab="Spearman Correlation of Views versus Quality")
abline(lm(sorted_quality_prediction_and_page_views$spearman_corr_of_views_versus_quality ~ sorted_quality_prediction_and_page_views$row_number))



In [52]:

    
cor(sorted_quality_prediction_and_page_views$row_number,sorted_quality_prediction_and_page_views$spearman_corr_of_views_versus_quality, method="spearman")



In [53]:

    
summary(lm(sorted_quality_prediction_and_page_views$spearman_corr_of_views_versus_quality ~ sorted_quality_prediction_and_page_views$row_number))









    





Call:
lm(formula = sorted_quality_prediction_and_page_views$spearman_corr_of_views_versus_quality ~ 
    sorted_quality_prediction_and_page_views$row_number)

Residuals:
      Min        1Q    Median        3Q       Max 
-0.125695 -0.053034 -0.000359  0.050621  0.183343 

Coefficients:
                                                      Estimate Std. Error
(Intercept)                                          0.2251899  0.0177499
sorted_quality_prediction_and_page_views$row_number -0.0024234  0.0005324
                                                    t value Pr(>|t|)    
(Intercept)                                          12.687  < 2e-16 ***
sorted_quality_prediction_and_page_views$row_number  -4.552 2.98e-05 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.06612 on 55 degrees of freedom
Multiple R-squared:  0.2737,	Adjusted R-squared:  0.2605 
F-statistic: 20.72 on 1 and 55 DF,  p-value: 2.98e-05



In [54]:

    
plot(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number, sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total, xlab="Month", ylab="Bot edits over total")
abline(lm(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total ~ sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number))



In [55]:

    
cor(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number, sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total, method="spearman")



In [56]:

    
summary(lm(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total ~ sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number))









    





Call:
lm(formula = sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total ~ 
    sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.84921 -0.04856  0.04118  0.08929  0.20414 

Coefficients:
                                                                            Estimate
(Intercept)                                                                 0.857224
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number -0.005370
                                                                           Std. Error
(Intercept)                                                                  0.043685
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number   0.001333
                                                                           t value
(Intercept)                                                                 19.623
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number  -4.027
                                                                           Pr(>|t|)
(Intercept)                                                                 < 2e-16
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number 0.000178
                                                                              
(Intercept)                                                                ***
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$row_number ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.1613 on 54 degrees of freedom
Multiple R-squared:  0.231,	Adjusted R-squared:  0.2167 
F-statistic: 16.22 on 1 and 54 DF,  p-value: 0.0001776



In [57]:

    
cor(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality, sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total, method="spearman")









    




0.289336978810663



In [58]:

    
summary(lm(sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total ~ sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality))









    





Call:
lm(formula = sorted_quality_predictions_and_page_views_and_monthly_bot_edits$prev_month_bot_edits_over_total ~ 
    sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.75313 -0.10393  0.03216  0.14159  0.22847 

Coefficients:
                                                                                                      Estimate
(Intercept)                                                                                            0.67228
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality  0.20560
                                                                                                      Std. Error
(Intercept)                                                                                              0.05516
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality    0.31850
                                                                                                      t value
(Intercept)                                                                                            12.187
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality   0.646
                                                                                                      Pr(>|t|)
(Intercept)                                                                                             <2e-16
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality    0.521
                                                                                                         
(Intercept)                                                                                           ***
sorted_quality_predictions_and_page_views_and_monthly_bot_edits$spearman_corr_of_views_versus_quality    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.1832 on 54 degrees of freedom
Multiple R-squared:  0.007658,	Adjusted R-squared:  -0.01072 
F-statistic: 0.4167 on 1 and 54 DF,  p-value: 0.5213



In [ ]:

yymm	prev_month_bot_edits_over_total	prev_month_bot_edits	prev_month_edits	spearman_corr_of_views_versus_quality	p	row_number
1211	0.002649431	703	265340	0.40610964	4.559667e-174	1
1212	0.439382794	183981	418726	0.16410131	0.000000e+00	2
1301	0.907962344	1949811	2147458	0.09222488	0.000000e+00	3
1302	0.922694936	2337846	2533715	0.14043395	0.000000e+00	4
1303	0.862359141	2327478	2698966	0.17557653	0.000000e+00	5
1304	0.903903559	8256322	9134074	0.22929523	0.000000e+00	6
1305	0.948170642	13900943	14660803	0.23063940	0.000000e+00	7
1306	0.940258291	14463573	15382553	0.25586321	0.000000e+00	8
1307	0.817919933	3850902	4708165	0.25671401	0.000000e+00	9
1308	0.918788902	8355311	9093831	0.26641139	0.000000e+00	10
1309	0.836895853	4091547	4888956	0.27332548	0.000000e+00	11
1310	0.869537443	5150692	5923485	0.27802750	0.000000e+00	12
1311	0.938626146	8500770	9056609	0.26782685	0.000000e+00	13
1312	0.883819379	6840625	7739845	0.25963683	0.000000e+00	14
1401	0.873717052	5688500	6510689	0.26579848	0.000000e+00	15
1402	0.905460154	8359698	9232541	0.27391589	0.000000e+00	16
1403	0.854197858	5062952	5927142	0.27164557	0.000000e+00	17
1404	0.867425753	4839056	5578640	0.20208494	0.000000e+00	18
1405	0.807545341	4412498	5464087	0.20141655	0.000000e+00	19
1406	0.854548731	9606783	11241937	0.17606298	0.000000e+00	20
1407	0.710971257	4310040	6062186	0.16898030	0.000000e+00	21
1408	0.657433561	4395942	6686519	0.15423070	0.000000e+00	22
1409	0.684800157	4053302	5918956	0.09475239	0.000000e+00	23
1410	0.679908395	4089341	6014547	0.05780762	0.000000e+00	24
1411	0.762452031	6653100	8725926	0.05964949	0.000000e+00	25
1412	0.809998497	6835681	8439128	0.04531066	0.000000e+00	26
1501	0.734080536	4978278	6781651	0.04630314	0.000000e+00	27
1502	0.749753801	5460241	7282712	0.09211579	0.000000e+00	28
1503	0.719331520	5341225	7425262	0.13049032	0.000000e+00	29
1504	0.778160065	6195498	7961727	0.13480227	0.000000e+00	30
1505	0.539082365	2914048	5405571	0.12512988	0.000000e+00	31
1506	0.730264168	5227607	7158515	0.11263627	0.000000e+00	32
1507	0.625321026	2866556	4584135	0.12586697	0.000000e+00	33
1508	0.878790677	11048877	12572820	0.06287843	0.000000e+00	34
1509	0.766204690	6627289	8649502	0.04692934	0.000000e+00	35
1510	0.741281404	5444726	7345019	0.04452854	0.000000e+00	36
1511	0.758349532	9315279	12283622	0.06394301	0.000000e+00	37
1512	0.677263809	7509707	11088304	0.06209993	0.000000e+00	38
1601	0.562167380	5350179	9517057	0.07764267	0.000000e+00	39
1602	0.540641446	5821280	10767358	0.09725208	0.000000e+00	40
1603	0.564259837	5680814	10067727	0.12001179	0.000000e+00	41
1604	0.554568941	4977396	8975252	0.12304755	0.000000e+00	42
1605	0.685493608	7032518	10259057	0.11738700	0.000000e+00	43
1606	0.725654544	10163437	14005889	0.11620185	0.000000e+00	44
1607	0.373705914	3919175	10487324	0.11903759	0.000000e+00	45
1608	0.572841083	4722664	8244283	0.14158668	0.000000e+00	46
1609	0.576158200	6172895	10713889	0.14027799	0.000000e+00	47
1610	0.329518100	3566783	10824240	0.14939584	0.000000e+00	48
1611	0.606654432	9851141	16238472	0.15221274	0.000000e+00	49
1612	0.613149457	8333936	13592014	0.15849012	0.000000e+00	50
1701	0.438299035	4478927	10218884	0.15245836	0.000000e+00	51
1702	0.465745975	7963334	17098020	0.15399518	0.000000e+00	52
1703	0.639370516	11542070	18052240	0.13894629	0.000000e+00	53
1704	0.631230587	8202274	12994101	0.14494673	0.000000e+00	54
1705	0.623490165	5456289	8751203	0.13676837	0.000000e+00	55
1706	0.572228020	121171	211753	0.13588080	0.000000e+00	56