Merge pull request #8 from drorhilman/master

recent work on analysing the data and attempting to create a simple model that predicts and explain the major causes of injury

datascience/data/2018_11_20_injury_risk_balanced_RF_classifier_full_03_permutations_importnace.csv

@@ -0,0 +1,132 @@
+feature,permutation_importance
+license_acquiring_date,0.03977586729236948
+accident_year,0.023580126194370554
+accident_month,0.015926662258545443
+age_group=1,0.0010306875596873821
+age_group=2,0.0006313894872327364
+age_group=3,0.0005896652482813014
+age_group=4,0.0037009232681299853
+age_group=5,0.004251952301798534
+age_group=6,0.0030287532802019124
+age_group=7,0.003775348373258103
+age_group=8,0.00342450877672007
+age_group=9,0.0019493307010973737
+age_group=10,0.001774963043451594
+age_group=11,0.0013736935917241233
+age_group=12,0.0009335791753142253
+age_group=13,0.0011324898001225936
+age_group=14,0.0011118044805449312
+age_group=15,0.0014528922940981737
+age_group=16,0.002412143029393743
+age_group=17,0.0011290681784063006
+age_group=99,0.042697734898774264
+sex=1.0,0.012598574669024476
+sex=2.0,0.009709432898258097
+vehicle_type=1.0,0.07683820424614773
+vehicle_type=2.0,0.004291153282676374
+vehicle_type=3.0,0.0023993629608364264
+vehicle_type=4.0,0.00043033336814202183
+vehicle_type=6.0,0.00013550806032203155
+vehicle_type=8.0,0.0005046841018626624
+vehicle_type=9.0,0.0023870284495011163
+vehicle_type=10.0,0.0014269841954530627
+vehicle_type=11.0,0.007385691160310626
+vehicle_type=12.0,0.003926367973302813
+vehicle_type=15.0,0.0020533315966043686
+vehicle_type=17.0,0.0010730777851946094
+vehicle_type=18.0,0.0004644513183910126
+vehicle_type=19.0,0.0031636392518927803
+safety_measures=1.0,0.012168331244642339
+safety_measures=2.0,0.002170262511683063
+safety_measures=4.0,0.0015006169900282362
+safety_measures=5.0,0.025081135312342684
+population_type=1.0,0.008593263057740996
+population_type=2.0,0.009478640298220542
+population_type=3.0,0.0005666310541285746
+population_type=4.0,0.0005084061625855174
+home_region=1.0,0.0012176357986860564
+home_region=2.0,0.009312587337068745
+home_region=3.0,0.0021470981004452216
+home_region=4.0,0.0057900357005844505
+home_region=5.0,0.003405913105747116
+home_region=6.0,0.0024419141454002924
+home_region=7.0,0.0017545130543379361
+home_district=11,0.0014965705947923569
+home_district=21,0.00027385686676550947
+home_district=22,0.00016662578208181955
+home_district=23,0.0017989782958082179
+home_district=24,0.0035734772563080774
+home_district=31,0.0012826507728722625
+home_district=32,0.0009575797950295284
+home_district=41,0.0007967803549167041
+home_district=42,0.0007838369109032239
+home_district=43,0.00022593805340753725
+home_district=44,0.0015415689208451155
+home_district=51,0.0025974627493623448
+home_district=61,0.000994724554162607
+home_district=62,0.0019685684631198797
+home_district=73,0.00016192534804326808
+home_district=74,5.10958417453411e-05
+home_district=76,0.00018363025397272192
+home_district=99,0.015482092404159209
+home_natural_area=111.0,0.0007211534937622277
+home_natural_area=112.0,0.00017686675172434718
+home_natural_area=221.0,9.417863420302375e-05
+home_natural_area=222.0,7.983542364686791e-05
+home_natural_area=234.0,0.0001311758587210221
+home_natural_area=237.0,0.0007663432523543623
+home_natural_area=241.0,0.0012646532950240097
+home_natural_area=242.0,0.0006450813438744207
+home_natural_area=243.0,0.00028485819678936153
+home_natural_area=245.0,0.0002683136462731106
+home_natural_area=246.0,0.00048164722282151295
+home_natural_area=311.0,0.00110552748006576
+home_natural_area=323.0,0.00023167002155100036
+home_natural_area=324.0,0.00029780164080284166
+home_natural_area=411.0,0.0003810733188076565
+home_natural_area=412.0,0.00018206832017375607
+home_natural_area=421.0,0.00043549640844364745
+home_natural_area=422.0,0.0004172011764772554
+home_natural_area=431.0,0.00025471884834527003
+home_natural_area=432.0,0.00010388920415138614
+home_natural_area=441.0,0.0003335493182818894
+home_natural_area=442.0,0.00022254301208590732
+home_natural_area=511.0,0.0006818073946690539
+home_natural_area=512.0,0.0007641565450358101
+home_natural_area=513.0,0.0004632044562401516
+home_natural_area=611.0,9.525138134414135e-05
+home_natural_area=612.0,0.0002047369667772525
+home_natural_area=613.0,0.0007362039039102708
+home_natural_area=614.0,0.0004176491500988977
+home_natural_area=623.0,0.0004124063686131718
+home_natural_area=730.0,0.000172614291307438
+home_natural_area=740.0,8.918044604611097e-05
+home_natural_area=760.0,0.0001561402191103678
+home_residence_type=9.0,0.00020931376170718607
+home_residence_type=10.0,0.00017539919175080243
+home_residence_type=11.0,0.0007703072215178297
+home_residence_type=12.0,0.0010454136353225119
+home_residence_type=13.0,0.001919329624403554
+home_residence_type=14.0,0.004362272619020446
+home_residence_type=15.0,0.0014116957699524812
+home_residence_type=16.0,0.003673439811244128
+home_residence_type=17.0,0.0008962429836416597
+home_residence_type=18.0,0.00037826183796940693
+home_residence_type=19.0,0.00017338928433030532
+home_residence_type=25.0,0.0006742542667560469
+home_residence_type=26.0,0.0013466900586310837
+home_residence_type=27.0,0.0016919598542820546
+home_residence_type=28.0,0.0011227699673093117
+home_residence_type=31.0,0.001271884773312415
+home_residence_type=33.0,0.00047477739899426386
+home_residence_type=37.0,0.0001947552231051919
+car_id=1.0,0.029386185040153223
+car_id=2.0,0.018027565378199273
+car_id=3.0,0.0012206067618922845
+car_id=4.0,0.00021649865718265104
+involve_id=1,0.016893569489955462
+involve_id=2,0.01052999049017922
+involve_id=3,0.0030648252921938735
+involve_id=4,0.0011571271411104922
+involve_id=5,0.0007254352194622227
+involve_id=6,0.0003522805761166925

datascience/data/embedding_num_cols.json

@@ -0,0 +1 @@
+{"license_acquiring_date": {"0.0": 0, "1977.0": 1, "1982.0": 2, "2006.0": 3, "2000.0": 4, "1989.0": 5, "1987.0": 6, "2012.0": 7, "2014.0": 8, "1985.0": 9, "2009.0": 10, "1980.0": 11, "2010.0": 12, "2002.0": 13, "2011.0": 14, "1986.0": 15, "1991.0": 16, "2005.0": 17, "1988.0": 18, "1967.0": 19, "1983.0": 20, "2013.0": 21, "1969.0": 22, "1999.0": 23, "1995.0": 24, "2004.0": 25, "1993.0": 26, "1973.0": 27, "1997.0": 28, "2015.0": 29, "2001.0": 30, "2007.0": 31, "1981.0": 32, "2003.0": 33, "1994.0": 34, "1998.0": 35, "1964.0": 36, "2008.0": 37, "1990.0": 38, "1996.0": 39, "1975.0": 40, "1992.0": 41, "1978.0": 42, "1974.0": 43, "1970.0": 44, "1984.0": 45, "1976.0": 46, "1972.0": 47, "1979.0": 48, "1968.0": 49, "1965.0": 50, "1971.0": 51, "1966.0": 52, "2017.0": 53, "2016.0": 54, "1963.0": 55, "2018.0": 56, "1962.0": 57, "1957.0": 58, "1961.0": 59, "1959.0": 60, "1956.0": 61, "1951.0": 62, "1958.0": 63, "1955.0": 64, "1953.0": 65, "1960.0": 66, "1952.0": 67, "1949.0": 68, "1950.0": 69, "1954.0": 70, "4444.0": 71, "1948.0": 72, "1911.0": 73, "3055.0": 74}, "accident_year": {"2009.0": 0, "2010.0": 1, "2015.0": 2, "2016.0": 3, "2014.0": 4, "2011.0": 5, "2012.0": 6, "2013.0": 7, "2017.0": 8, "2008.0": 9, "2018.0": 10}, "accident_month": {"4.0": 0, "11.0": 1, "6.0": 2, "10.0": 3, "5.0": 4, "12.0": 5, "1.0": 6, "7.0": 7, "9.0": 8, "3.0": 9, "8.0": 10, "2.0": 11}, "age_group": {"99.0": 0, "12.0": 1, "5.0": 2, "10.0": 3, "7.0": 4, "9.0": 5, "8.0": 6, "6.0": 7, "11.0": 8, "13.0": 9, "4.0": 10, "15.0": 11, "14.0": 12, "16.0": 13, "17.0": 14, "18.0": 15, "3.0": 16, "2.0": 17, "1.0": 18}, "sex": {"1.0": 0, "2.0": 1}, "vehicle_type": {"1.0": 0, "3.0": 1, "17.0": 2, "11.0": 3, "10.0": 4, "4.0": 5, "2.0": 6, "6.0": 7, "18.0": 8, "15.0": 9, "19.0": 10, "12.0": 11, "8.0": 12, "7.0": 13, "9.0": 14, "14.0": 15, "16.0": 16, "5.0": 17, "13.0": 18}, "safety_measures": {"5.0": 0, "2.0": 1, "4.0": 2, "1.0": 3, "3.0": 4}, "population_type": {"1.0": 0, "4.0": 1, "2.0": 2, "3.0": 3}, "home_region": {"3.0": 0, "4.0": 1, "7.0": 2, "5.0": 3, "2.0": 4, "6.0": 5, "1.0": 6, "8.0": 7}, "home_district": {"99.0": 0, "77.0": 1, "71.0": 2, "74.0": 3, "73.0": 4, "72.0": 5, "76.0": 6, "75.0": 7, "51.0": 8, "21.0": 9, "32.0": 10, "24.0": 11, "61.0": 12, "41.0": 13, "23.0": 14, "43.0": 15, "11.0": 16, "22.0": 17, "62.0": 18, "29.0": 19, "42.0": 20, "31.0": 21, "44.0": 22, "87.0": 23, "86.0": 24, "81.0": 25, "80.0": 26}, "home_natural_area": {"336.0": 0, "337.0": 1, "390.0": 2, "393.0": 3, "391.0": 4, "341.0": 5, "340.0": 6, "394.0": 7, "338.0": 8, "770.0": 9, "395.0": 10, "710.0": 11, "740.0": 12, "730.0": 13, "720.0": 14, "760.0": 15, "750.0": 16, "389.0": 17, "512.0": 18, "392.0": 19, "211.0": 20, "324.0": 21, "246.0": 22, "614.0": 23, "412.0": 24, "245.0": 25, "234.0": 26, "232.0": 27, "432.0": 28, "431.0": 29, "411.0": 30, "112.0": 31, "221.0": 32, "321.0": 33, "622.0": 34, "611.0": 35, "625.0": 36, "241.0": 37, "212.0": 38, "293.0": 39, "623.0": 40, "111.0": 41, "222.0": 42, "422.0": 43, "421.0": 44, "244.0": 45, "294.0": 46, "242.0": 47, "612.0": 48, "311.0": 49, "621.0": 50, "292.0": 51, "513.0": 52, "441.0": 53, "213.0": 54, "233.0": 55, "243.0": 56, "323.0": 57, "237.0": 58, "231.0": 59, "322.0": 60, "626.0": 61, "442.0": 62, "613.0": 63, "236.0": 64, "235.0": 65, "511.0": 66, "624.0": 67, "291.0": 68, "627.0": 69, "999.0": 70, "339.0": 71, "870.0": 72, "860.0": 73, "342.0": 74, "810.0": 75, "800.0": 76}, "home_residence_type": {"17.0": 0, "18.0": 1, "29.0": 2, "49.0": 3, "31.0": 4, "34.0": 5, "59.0": 6, "9.0": 7, "35.0": 8, "33.0": 9, "27.0": 10, "45.0": 11, "28.0": 12, "37.0": 13, "15.0": 14, "19.0": 15, "16.0": 16, "32.0": 17, "25.0": 18, "26.0": 19, "13.0": 20, "51.0": 21, "14.0": 22, "11.0": 23, "12.0": 24, "46.0": 25, "53.0": 26, "10.0": 27, "52.0": 28, "44.0": 29}, "car_id": {"1.0": 0, "2.0": 1, "3.0": 2, "5.0": 3, "4.0": 4, "7.0": 5, "13.0": 6, "10.0": 7, "6.0": 8, "11.0": 9, "9.0": 10, "12.0": 11, "8.0": 12, "17.0": 13, "15.0": 14, "18.0": 15, "14.0": 16, "19.0": 17, "21.0": 18, "20.0": 19, "16.0": 20, "28.0": 21, "25.0": 22, "27.0": 23, "23.0": 24, "29.0": 25, "22.0": 26, "30.0": 27, "26.0": 28, "24.0": 29}, "involve_id": {"4.0": 0, "3.0": 1, "1.0": 2, "2.0": 3, "5.0": 4, "6.0": 5, "8.0": 6, "7.0": 7, "10.0": 8, "9.0": 9, "11.0": 10, "15.0": 11, "26.0": 12, "12.0": 13, "58.0": 14, "13.0": 15, "30.0": 16, "16.0": 17, "14.0": 18, "19.0": 19, "20.0": 20, "17.0": 21, "18.0": 22, "29.0": 23, "73.0": 24, "25.0": 25, "21.0": 26, "23.0": 27, "77.0": 28, "60.0": 29, "50.0": 30, "31.0": 31, "45.0": 32, "49.0": 33, "22.0": 34, "28.0": 35, "65.0": 36, "54.0": 37, "56.0": 38, "66.0": 39, "34.0": 40, "52.0": 41, "63.0": 42, "53.0": 43, "61.0": 44, "78.0": 45, "37.0": 46, "48.0": 47, "36.0": 48, "46.0": 49, "38.0": 50, "27.0": 51, "24.0": 52, "41.0": 53, "47.0": 54, "39.0": 55, "43.0": 56, "44.0": 57, "51.0": 58, "33.0": 59, "32.0": 60, "67.0": 61, "35.0": 62, "42.0": 63, "59.0": 64, "55.0": 65, "57.0": 66, "71.0": 67, "72.0": 68, "40.0": 69, "68.0": 70, "64.0": 71, "76.0": 72, "69.0": 73, "70.0": 74, "62.0": 75, "79.0": 76, "75.0": 77, "74.0": 78}}