- Revision 39706: /other-projects/maori-lang-detection/mongodb-data

• ..
• 1a_counts_miInUrlPath.json
• 1a_geojson-features_miInUrlPath.json
• 1a_multipoint_miInUrlPath.json
• 1a_table_miInUrlPath.csv
• 1a_table_miInUrlPath.png
• 1b_counts_noMiInUrlPath.json
• 1b_geojson-features_noMiInUrlPath.json
• 1b_multipoint_noMiInUrlPath.json
• 1b_table_noMiInUrlPath.csv
• 1b_table_noMiInUrlPath.png
• 1counts_allCrawledSites.json
• 1geojson-features_allCrawledSites.json
• 1map_allCrawledSites.png
• 1multipoint_allCrawledSites.json
• 1table_allCrawledSites.csv
• 1table_allCrawledSites.png
• 2counts_sitesWithPagesInMRI.json
• 2geojson-features_sitesWithPagesInMRI.json
• 2map_sitesWithPagesInMRI.png
• 2multipoint_sitesWithPagesInMRI.json
• 2table_sitesWithPagesInMRI.csv
• 2table_sitesWithPagesInMRI.png
• 3counts_sitesWithPagesContainingMRI.json
• 3geojson-features_sitesWithPagesContainingMRI.json
• 3map_sitesWithPagesContainingMRI.png
• 3multipoint_sitesWithPagesContainingMRI.json
• 3table_sitesWithPagesContainingMRI.csv
• 3table_sitesWithPagesContainingMRI.png
• 4counts_tentativeNonProductSites.json
• 4geojson-features_tentativeNonProductSites.json
• 4map_exclTentativeAutotranslatedSites.png
• 4multipoint_tentativeNonProductSites.json
• 4table_tentativeNonProductSites.csv
• 4table_tentativeNonProductSites.png
• 5b_counts_containsMRI_groupedByNZorOverseasNoFilter.json
• 5b_geojson-features_containsMRI_groupedByNZorOverseasNoFilter.json
• 5b_map_containsMRI_groupedByNZorOverseasNoFilter.png
• 5b_multipoint_containsMRI_groupedByNZorOverseasNoFilter.json
• 5b_table_containsMRI_groupedByNZorOverseasNoFilter.csv
• 5b_table_containsMRI_groupedByNZorOverseasNoFilter.png
• 5counts_tentativeNonProductSites1.json
• 5geojson-features_tentativeNonProductSites1.json
• 5map_exclTentativeAutotranslatedSites1.png
• 5multipoint_tentativeNonProductSites1.json
• 5table_tentativeNonProductSites1.csv
• 5table_tentativeNonProductSites1.png
• 6a_counts_manualShortlist_numPagesInMRI.json
• 6a_geojson-features_manualShortlist_numPagesInMRI.json
• 6a_map_numPagesInMRI_fromManualInspectedSites.png
• 6a_multipoint_manualShortlist_numPagesInMRI.json
• 6b_counts_manualShortlist_numPagesContainingMRI.json
• 6b_geojson-features_manualShortlist_numPagesContainingMRI.json
• 6b_map_numPagesContainingMRI_fromManualInspectedSites.png
• 6b_multipoint_manualShortlist_numPagesContainingMRI.json
• 6counts_nonProductSites1_manualShortlist.json
• 6counts_sitesWithPagesContainingMRI_manualShortlist.json
• 6counts_sitesWithPagesContainingMRI_manualShortlist.jsonOLD
• 6geojson-features_sitesWithPagesContainingMRI_manualShortlist.json
• 6map_sitesWithPagesContainingMRI_manualShortlist.png
• 6multipoint_sitesWithPagesContainingMRI_manualShortlist.json
• 6table_nonProductSites1_manualShortlist.json
• 7miInURLPath_exclNZ_byCountryCode.json
• 8TableOfNumDetectedVsManualSITESWithMRI.ods
• 8table_siteCountSummary.png
• InfoOnEmptyPagesNotInMongoDB.csv
• InfoOnEmptyPagesNotInMongoDB.ods
• ManualShortlisting.txt
• ManualShortlisting2_afterMongoDBReingest.txt
• googlescholar.txt
• isMRI_full_manualList_globalDomains_whereAPageContainsMRI.txt
• manualList_globalDomains_whereAPageContainsMRI.txt
• pieChart01a_seedURLsForCrawling.png
• pieChart01b_obtainingSeedURLs.png
• pieChart01c_obtainingSeedURLs.svg
• pieChart2a_CrawledWebPages_EmptyVsInMongoDB.png
• pieChart2b_CrawledWebPages_EmptyVsInMongoDB.svg
• pieChart3a_SimplerCrawledWebPages_EmptyVsInMongoDB.png
• pieChart3b_SimplerCrawledWebPages_EmptyVsInMongoDB.svg
• pieChart3c_screenshot_SimplerCrawledWebPages_EmptyVsInMongoDB.png
• pieChart4a_sitesPreparedForCrawling.png
• pieChart4b_sitesPreparedForCrawling.svg
• pieChart4c_screenshotSitesPreparedForCrawling.png
• pieChart5a_sitesPreparedForCrawling.png
• pieChart5b_sitesPreparedForCrawling.svg
• pieChart5c_screenshotSitesPreparedForCrawling.png
• piechart_data.txt
• piechart_data2.txt
• random260.csv
• random260.ods
• random260_manualList_globalDomains_whereAPageContainsMRI.txt
• random260_results.txt
• tables.txt