C4.5 [release 8] decision tree generator Fri Jun 1 10:14:31 2001 ---------------------------------------- Options: File stem Read 4142 cases (57 attributes) from sb2.data.6.data Decision Tree: word_freq_remove <= 0 : | char_freq_$ <= 0.055 : | | word_freq_000 <= 0.25 : | | | char_freq_! <= 0.378 : | | | | word_freq_money <= 0.03 : | | | | | word_freq_font <= 0.12 : | | | | | | word_freq_free <= 0.1 : | | | | | | | word_freq_george > 0 : 0 (593.0) | | | | | | | word_freq_george <= 0 : | | | | | | | | word_freq_our <= 0.71 : | | | | | | | | | word_freq_hp <= 0.02 : | | | | | | | | | | word_freq_business <= 0.08 : | | | | | | | | | | | word_freq_technology <= 0.22 :[S1] | | | | | | | | | | | word_freq_technology > 0.22 : | | | | | | | | | | | | word_freq_650 > 0.13 : 1 (4.0) | | | | | | | | | | | | word_freq_650 <= 0.13 :[S2] | | | | | | | | | | word_freq_business > 0.08 : | | | | | | | | | | | word_freq_hp > 0 : 1 (2.0) | | | | | | | | | | | word_freq_hp <= 0 : | | | | | | | | | | | | word_freq_make > 0.2 : 1 (4.0) | | | | | | | | | | | | word_freq_make <= 0.2 :[S3] | | | | | | | | | word_freq_hp > 0.02 : | | | | | | | | | | word_freq_receive <= 0.1 : 0 (451.0/3.0) | | | | | | | | | | word_freq_receive > 0.1 : | | | | | | | | | | | char_freq_$ <= 0.039 : 0 (31.0/1.0) | | | | | | | | | | | char_freq_$ > 0.039 : 1 (2.0) | | | | | | | | word_freq_our > 0.71 : | | | | | | | | | word_freq_internet <= 0.33 : | | | | | | | | | | word_freq_email <= 0.43 : | | | | | | | | | | | capital_run_length_average <= 3.675 : | | | | | | | | | | | | word_freq_pm > 0.04 : 0 (6.0) | | | | | | | | | | | | word_freq_pm <= 0.04 :[S4] | | | | | | | | | | | capital_run_length_average > 3.675 : | | | | | | | | | | | | word_freq_will <= 0.4 : 1 (5.0) | | | | | | | | | | | | word_freq_will > 0.4 : 0 (2.0) | | | | | | | | | | word_freq_email > 0.43 : | | | | | | | | | | | word_freq_will <= 1.82 : 1 (5.0) | | | | | | | | | | | word_freq_will > 1.82 : 0 (2.0) | | | | | | | | | word_freq_internet > 0.33 : | | | | | | | | | | word_freq_over <= 0.07 : 1 (8.0) | | | | | | | | | | word_freq_over > 0.07 : 0 (4.0/1.0) | | | | | | word_freq_free > 0.1 : | | | | | | | word_freq_george > 0 : 0 (32.0) | | | | | | | word_freq_george <= 0 : | | | | | | | | word_freq_people > 0.17 : 0 (20.0) | | | | | | | | word_freq_people <= 0.17 : | | | | | | | | | word_freq_our <= 1.13 : | | | | | | | | | | word_freq_85 > 0.06 : 0 (8.0) | | | | | | | | | | word_freq_85 <= 0.06 : | | | | | | | | | | | word_freq_650 > 0.13 : 1 (8.0/1.0) | | | | | | | | | | | word_freq_650 <= 0.13 :[S5] | | | | | | | | | word_freq_our > 1.13 : | | | | | | | | | | word_freq_meeting > 0.71 : 0 (2.0) | | | | | | | | | | word_freq_meeting <= 0.71 : | | | | | | | | | | | char_freq_! <= 0.279 : 1 (23.0) | | | | | | | | | | | char_freq_! > 0.279 : 0 (2.0) | | | | | word_freq_font > 0.12 : | | | | | | char_freq_; > 0.895 : 0 (15.0) | | | | | | char_freq_; <= 0.895 : | | | | | | | word_freq_edu <= 0.09 : 1 (19.0) | | | | | | | word_freq_edu > 0.09 : 0 (5.0) | | | | word_freq_money > 0.03 : | | | | | word_freq_hp > 0.08 : 0 (12.0) | | | | | word_freq_hp <= 0.08 : | | | | | | word_freq_edu > 0.08 : 0 (9.0) | | | | | | word_freq_edu <= 0.08 : | | | | | | | word_freq_project > 0.18 : 0 (4.0) | | | | | | | word_freq_project <= 0.18 : | | | | | | | | capital_run_length_longest <= 9 : 0 (5.0/1.0) | | | | | | | | capital_run_length_longest > 9 : 1 (27.0/1.0) | | | char_freq_! > 0.378 : | | | | capital_run_length_total <= 64 : | | | | | word_freq_free > 0.77 : 1 (19.0/1.0) | | | | | word_freq_free <= 0.77 : | | | | | | word_freq_hp > 0.5 : 0 (8.0) | | | | | | word_freq_hp <= 0.5 : | | | | | | | word_freq_george > 0.58 : 0 (8.0) | | | | | | | word_freq_george <= 0.58 : | | | | | | | | word_freq_business > 0.27 : 1 (7.0/1.0) | | | | | | | | word_freq_business <= 0.27 : | | | | | | | | | word_freq_money <= 0.23 : | | | | | | | | | | word_freq_re > 0.34 : 0 (27.0) | | | | | | | | | | word_freq_re <= 0.34 : | | | | | | | | | | | char_freq_! <= 0.983 :[S6] | | | | | | | | | | | char_freq_! > 0.983 : | | | | | | | | | | | | word_freq_you <= 0.65 : 0 (13.0/2.0) | | | | | | | | | | | | word_freq_you > 0.65 : 1 (13.0/1.0) | | | | | | | | | word_freq_money > 0.23 : | | | | | | | | | | char_freq_! <= 0.511 : 0 (3.0) | | | | | | | | | | char_freq_! > 0.511 : 1 (4.0) | | | | capital_run_length_total > 64 : | | | | | char_freq_( <= 0.164 : | | | | | | char_freq_! <= 2.362 : | | | | | | | char_freq_; > 0.022 : 1 (8.0) | | | | | | | char_freq_; <= 0.022 : | | | | | | | | word_freq_your > 0.58 : 1 (85.0) | | | | | | | | word_freq_your <= 0.58 : | | | | | | | | | word_freq_email <= 0.18 : 1 (20.0/1.0) | | | | | | | | | word_freq_email > 0.18 : | | | | | | | | | | word_freq_address <= 0.23 : 0 (2.0) | | | | | | | | | | word_freq_address > 0.23 : 1 (2.0) | | | | | | char_freq_! > 2.362 : | | | | | | | capital_run_length_total <= 80 : 0 (2.0) | | | | | | | capital_run_length_total > 80 : 1 (5.0/1.0) | | | | | char_freq_( > 0.164 : | | | | | | word_freq_hp > 0.22 : 0 (5.0) | | | | | | word_freq_hp <= 0.22 : | | | | | | | word_freq_meeting > 0.09 : 0 (2.0) | | | | | | | word_freq_meeting <= 0.09 : | | | | | | | | word_freq_edu > 0.06 : 0 (2.0) | | | | | | | | word_freq_edu <= 0.06 : | | | | | | | | | word_freq_addresses > 0.09 : 1 (7.0) | | | | | | | | | word_freq_addresses <= 0.09 : | | | | | | | | | | word_freq_people > 0.31 : 0 (2.0) | | | | | | | | | | word_freq_people <= 0.31 : | | | | | | | | | | | char_freq_! > 0.68 : 1 (17.0) | | | | | | | | | | | char_freq_! <= 0.68 : | | | | | | | | | | | | word_freq_our > 0.08 : 1 (2.0) | | | | | | | | | | | | word_freq_our <= 0.08 : | | | | | | | | | | | | | char_freq_[ <= 0.042 : 0 (4.0) | | | | | | | | | | | | | char_freq_[ > 0.042 : 1 (2.0) | | word_freq_000 > 0.25 : | | | char_freq_( > 0.6 : 0 (3.0) | | | char_freq_( <= 0.6 : | | | | word_freq_hp > 0.67 : 0 (3.0/1.0) | | | | word_freq_hp <= 0.67 : | | | | | word_freq_our <= 0.83 : 1 (43.0/1.0) | | | | | word_freq_our > 0.83 : | | | | | | word_freq_you <= 1.79 : 0 (2.0) | | | | | | word_freq_you > 1.79 : 1 (3.0) | char_freq_$ > 0.055 : | | word_freq_hp > 0.39 : 0 (60.0/1.0) | | word_freq_hp <= 0.39 : | | | word_freq_edu <= 0.04 : | | | | capital_run_length_longest <= 9 : | | | | | word_freq_email > 1.43 : 1 (5.0) | | | | | word_freq_email <= 1.43 : | | | | | | capital_run_length_average <= 2.053 : 0 (18.0) | | | | | | capital_run_length_average > 2.053 : 1 (3.0) | | | | capital_run_length_longest > 9 : | | | | | char_freq_! > 0.377 : 1 (224.0) | | | | | char_freq_! <= 0.377 : | | | | | | word_freq_1999 <= 0 : | | | | | | | char_freq_! > 0.066 : 1 (163.0/2.0) | | | | | | | char_freq_! <= 0.066 : | | | | | | | | word_freq_hp > 0.14 : 0 (4.0/1.0) | | | | | | | | word_freq_hp <= 0.14 : | | | | | | | | | word_freq_hp > 0.02 : 1 (5.0) | | | | | | | | | word_freq_hp <= 0.02 : | | | | | | | | | | word_freq_labs > 0.12 : 1 (4.0) | | | | | | | | | | word_freq_labs <= 0.12 : | | | | | | | | | | | word_freq_original > 0.03 : 1 (5.0) | | | | | | | | | | | word_freq_original <= 0.03 :[S7] | | | | | | word_freq_1999 > 0 : | | | | | | | word_freq_conference > 0.32 : 0 (2.0) | | | | | | | word_freq_conference <= 0.32 : | | | | | | | | word_freq_order > 0.41 : 0 (2.0) | | | | | | | | word_freq_order <= 0.41 : | | | | | | | | | word_freq_free <= 0.61 : 1 (7.0) | | | | | | | | | word_freq_free > 0.61 : 0 (2.0) | | | word_freq_edu > 0.04 : | | | | word_freq_addresses > 0.08 : 1 (5.0) | | | | word_freq_addresses <= 0.08 : | | | | | char_freq_; <= 0.151 : 0 (18.0) | | | | | char_freq_; > 0.151 : 1 (2.0) word_freq_remove > 0 : | word_freq_hp <= 0.19 : | | word_freq_1999 <= 0.22 : | | | word_freq_over > 0.25 : 1 (214.0) | | | word_freq_over <= 0.25 : | | | | word_freq_000 > 0.2 : 1 (125.0) | | | | word_freq_000 <= 0.2 : | | | | | word_freq_addresses > 0.03 : 1 (53.0) | | | | | word_freq_addresses <= 0.03 : | | | | | | word_freq_000 <= 0.02 : | | | | | | | char_freq_! <= 0.077 : | | | | | | | | word_freq_george > 0.11 : 0 (4.0) | | | | | | | | word_freq_george <= 0.11 : | | | | | | | | | word_freq_over > 0.13 : 0 (3.0/1.0) | | | | | | | | | word_freq_over <= 0.13 : | | | | | | | | | | word_freq_data <= 0.26 : 1 (46.0/2.0) | | | | | | | | | | word_freq_data > 0.26 : | | | | | | | | | | | word_freq_our <= 0.9 : 0 (2.0) | | | | | | | | | | | word_freq_our > 0.9 : 1 (2.0) | | | | | | | char_freq_! > 0.077 : | | | | | | | | word_freq_your > 0.32 : 1 (154.0/1.0) | | | | | | | | word_freq_your <= 0.32 : | | | | | | | | | word_freq_pm > 0.11 : 1 (2.0/1.0) | | | | | | | | | word_freq_pm <= 0.11 : | | | | | | | | | | word_freq_technology > 0.45 : 1 (2.0/1.0) | | | | | | | | | | word_freq_technology <= 0.45 : | | | | | | | | | | | word_freq_email <= 0.59 : 1 (33.0/1.0) | | | | | | | | | | | word_freq_email > 0.59 : 0 (3.0/1.0) | | | | | | word_freq_000 > 0.02 : | | | | | | | word_freq_you <= 3.55 : 1 (11.0) | | | | | | | word_freq_you > 3.55 : 0 (3.0/1.0) | | word_freq_1999 > 0.22 : | | | word_freq_george > 0.08 : 0 (3.0) | | | word_freq_george <= 0.08 : | | | | char_freq_; <= 0.008 : 1 (29.0) | | | | char_freq_; > 0.008 : | | | | | word_freq_our <= 0.22 : 0 (2.0) | | | | | word_freq_our > 0.22 : 1 (2.0) | word_freq_hp > 0.19 : | | char_freq_$ <= 0.028 : 0 (14.0) | | char_freq_$ > 0.028 : 1 (12.0/2.0) Subtree [S1] capital_run_length_average <= 2.674 : | capital_run_length_longest <= 21 : | | capital_run_length_average <= 1.55 : 0 (371.0/21.0) | | capital_run_length_average > 1.55 : | | | word_freq_you <= 3.75 : 0 (285.0) | | | word_freq_you > 3.75 : | | | | word_freq_over <= 0.94 : 0 (35.0/1.0) | | | | word_freq_over > 0.94 : 1 (2.0) | capital_run_length_longest > 21 : | | word_freq_650 > 0.32 : 1 (3.0) | | word_freq_650 <= 0.32 : | | | word_freq_order <= 0.29 : 0 (33.0/2.0) | | | word_freq_order > 0.29 : 1 (2.0) capital_run_length_average > 2.674 : | word_freq_edu > 0.26 : 0 (48.0/1.0) | word_freq_edu <= 0.26 : | | word_freq_receive > 0.99 : 0 (10.0) | | word_freq_receive <= 0.99 : | | | word_freq_over > 0.39 : 1 (4.0) | | | word_freq_over <= 0.39 : | | | | word_freq_85 > 0.04 : 0 (4.0) | | | | word_freq_85 <= 0.04 : | | | | | word_freq_conference > 0.37 : 0 (4.0) | | | | | word_freq_conference <= 0.37 : | | | | | | word_freq_project > 0.41 : 0 (4.0) | | | | | | word_freq_project <= 0.41 : | | | | | | | char_freq_# > 0.011 : 0 (3.0) | | | | | | | char_freq_# <= 0.011 : | | | | | | | | word_freq_re > 1.06 : 0 (3.0) | | | | | | | | word_freq_re <= 1.06 : | | | | | | | | | word_freq_meeting > 0.22 : 0 (4.0) | | | | | | | | | word_freq_meeting <= 0.22 : | | | | | | | | | | word_freq_pm > 0.24 : 0 (5.0) | | | | | | | | | | word_freq_pm <= 0.24 :[S8] Subtree [S2] word_freq_will <= 0.51 : 0 (12.0) word_freq_will > 0.51 : | word_freq_lab > 0.01 : 0 (2.0) | word_freq_lab <= 0.01 : | | word_freq_all > 0.74 : 0 (2.0) | | word_freq_all <= 0.74 : | | | capital_run_length_longest <= 5 : 0 (2.0) | | | capital_run_length_longest > 5 : 1 (4.0) Subtree [S3] word_freq_650 > 0.74 : 1 (2.0) word_freq_650 <= 0.74 : | word_freq_over > 0.3 : 1 (2.0) | word_freq_over <= 0.3 : | | word_freq_address <= 0.56 : 0 (20.0) | | word_freq_address > 0.56 : 1 (2.0) Subtree [S4] word_freq_technology > 0.03 : 0 (5.0) word_freq_technology <= 0.03 : | capital_run_length_longest <= 10 : 0 (67.0/3.0) | capital_run_length_longest > 10 : | | word_freq_hp > 0.11 : 0 (13.0) | | word_freq_hp <= 0.11 : | | | word_freq_re > 0.16 : 0 (2.0) | | | word_freq_re <= 0.16 : | | | | char_freq_! <= 0.112 : 1 (6.0) | | | | char_freq_! > 0.112 : 0 (3.0/1.0) Subtree [S5] word_freq_business > 0.69 : 1 (7.0/1.0) word_freq_business <= 0.69 : | word_freq_lab > 0 : 0 (8.0) | word_freq_lab <= 0 : | | word_freq_cs > 0.08 : 0 (7.0) | | word_freq_cs <= 0.08 : | | | word_freq_pm > 0.04 : 0 (7.0) | | | word_freq_pm <= 0.04 : | | | | word_freq_make > 0.21 : 0 (11.0) | | | | word_freq_make <= 0.21 : | | | | | capital_run_length_longest <= 42 : | | | | | | word_freq_meeting > 0.4 : 0 (3.0) | | | | | | word_freq_meeting <= 0.4 : | | | | | | | word_freq_project > 0.4 : 0 (4.0) | | | | | | | word_freq_project <= 0.4 : | | | | | | | | word_freq_hp > 1.36 : 0 (4.0) | | | | | | | | word_freq_hp <= 1.36 : | | | | | | | | | word_freq_business > 0.08 : 1 (3.0) | | | | | | | | | word_freq_business <= 0.08 : | | | | | | | | | | word_freq_1999 > 0.17 : 0 (3.0/1.0) | | | | | | | | | | word_freq_1999 <= 0.17 : | | | | | | | | | | | word_freq_telnet > 0.13 : 0 (2.0) | | | | | | | | | | | word_freq_telnet <= 0.13 : | | | | | | | | | | | | word_freq_over > 0.09 : 1 (2.0) | | | | | | | | | | | | word_freq_over <= 0.09 :[S9] | | | | | capital_run_length_longest > 42 : | | | | | | word_freq_mail <= 0.47 : 0 (27.0) | | | | | | word_freq_mail > 0.47 : 1 (3.0) Subtree [S6] capital_run_length_total > 48 : 1 (4.0/1.0) capital_run_length_total <= 48 : | word_freq_85 > 1.31 : 0 (4.0) | word_freq_85 <= 1.31 : | | word_freq_pm > 1.6 : 0 (3.0) | | word_freq_pm <= 1.6 : | | | word_freq_project > 0.31 : 0 (3.0) | | | word_freq_project <= 0.31 : | | | | word_freq_our > 0.87 : 0 (3.0) | | | | word_freq_our <= 0.87 : | | | | | word_freq_conference > 0.39 : 0 (3.0) | | | | | word_freq_conference <= 0.39 : | | | | | | capital_run_length_longest <= 8 : 0 (36.0/1.0) | | | | | | capital_run_length_longest > 8 : | | | | | | | capital_run_length_longest > 9 : 0 (7.0) | | | | | | | capital_run_length_longest <= 9 : | | | | | | | | word_freq_will <= 1.92 : 1 (3.0) | | | | | | | | word_freq_will > 1.92 : 0 (2.0) Subtree [S7] word_freq_internet > 0.01 : 1 (14.0) word_freq_internet <= 0.01 : | capital_run_length_average > 3.925 : 1 (24.0) | capital_run_length_average <= 3.925 : | | word_freq_receive > 0.1 : 1 (2.0) | | word_freq_receive <= 0.1 : | | | word_freq_direct > 0.77 : 1 (2.0) | | | word_freq_direct <= 0.77 : | | | | word_freq_000 > 0.3 : 1 (2.0) | | | | word_freq_000 <= 0.3 : | | | | | word_freq_free > 0.13 : 1 (2.0) | | | | | word_freq_free <= 0.13 : | | | | | | word_freq_email > 0.16 : 0 (2.0) | | | | | | word_freq_email <= 0.16 : | | | | | | | capital_run_length_average <= 2.272 : 0 (4.0) | | | | | | | capital_run_length_average > 2.272 : 1 (9.0/1.0) Subtree [S8] capital_run_length_total <= 30 : 0 (12.0/1.0) capital_run_length_total > 30 : | word_freq_650 > 4.16 : 1 (2.0) | word_freq_650 <= 4.16 : | | word_freq_email > 0.9 : 1 (2.0) | | word_freq_email <= 0.9 : | | | char_freq_; > 0.151 : 1 (2.0) | | | char_freq_; <= 0.151 : | | | | word_freq_address > 0.12 : 0 (2.0) | | | | word_freq_address <= 0.12 : | | | | | char_freq_[ > 0.038 : 1 (2.0) | | | | | char_freq_[ <= 0.038 : | | | | | | word_freq_mail > 0.04 : 1 (4.0) | | | | | | word_freq_mail <= 0.04 : | | | | | | | word_freq_make > 1.49 : 1 (2.0) | | | | | | | word_freq_make <= 1.49 : | | | | | | | | word_freq_all <= 1.13 : 0 (12.0/4.0) | | | | | | | | word_freq_all > 1.13 : 1 (2.0) Subtree [S9] word_freq_technology > 0.11 : 1 (2.0) word_freq_technology <= 0.11 : | word_freq_report > 0.26 : 1 (2.0) | word_freq_report <= 0.26 : | | word_freq_credit > 0.49 : 1 (2.0) | | word_freq_credit <= 0.49 : | | | word_freq_email > 0.49 : 1 (3.0) | | | word_freq_email <= 0.49 : | | | | word_freq_internet > 0.54 : 1 (4.0) | | | | word_freq_internet <= 0.54 : | | | | | capital_run_length_average > 3.791 : 1 (5.0) | | | | | capital_run_length_average <= 3.791 : | | | | | | word_freq_mail > 0.28 : 0 (4.0) | | | | | | word_freq_mail <= 0.28 : | | | | | | | capital_run_length_average <= 1.292 : 0 (6.0/1.0) | | | | | | | capital_run_length_average > 1.292 : 1 (7.0/1.0) Simplified Decision Tree: word_freq_remove <= 0 : | char_freq_$ <= 0.055 : | | word_freq_000 <= 0.25 : | | | char_freq_! <= 0.378 : | | | | word_freq_money <= 0.03 : | | | | | word_freq_font <= 0.12 : | | | | | | word_freq_free <= 0.1 : | | | | | | | word_freq_george > 0 : 0 (593.0/1.4) | | | | | | | word_freq_george <= 0 : | | | | | | | | word_freq_our <= 0.71 : | | | | | | | | | word_freq_hp > 0.02 : 0 (484.0/8.5) | | | | | | | | | word_freq_hp <= 0.02 : | | | | | | | | | | word_freq_business <= 0.08 : | | | | | | | | | | | word_freq_technology <= 0.22 :[S1] | | | | | | | | | | | word_freq_technology > 0.22 : | | | | | | | | | | | | word_freq_will <= 0.51 : 0 (13.0/2.5) | | | | | | | | | | | | word_freq_will > 0.51 :[S2] | | | | | | | | | | word_freq_business > 0.08 : | | | | | | | | | | | word_freq_hp > 0 : 1 (2.0/1.0) | | | | | | | | | | | word_freq_hp <= 0 : | | | | | | | | | | | | word_freq_make > 0.2 : 1 (4.0/1.2) | | | | | | | | | | | | word_freq_make <= 0.2 :[S3] | | | | | | | | word_freq_our > 0.71 : | | | | | | | | | word_freq_internet <= 0.33 : | | | | | | | | | | word_freq_email <= 0.43 : | | | | | | | | | | | capital_run_length_average <= 3.675 :[S4] | | | | | | | | | | | capital_run_length_average > 3.675 : | | | | | | | | | | | | word_freq_will <= 0.4 : 1 (5.0/1.2) | | | | | | | | | | | | word_freq_will > 0.4 : 0 (2.0/1.0) | | | | | | | | | | word_freq_email > 0.43 : | | | | | | | | | | | word_freq_will <= 1.82 : 1 (5.0/1.2) | | | | | | | | | | | word_freq_will > 1.82 : 0 (2.0/1.0) | | | | | | | | | word_freq_internet > 0.33 : | | | | | | | | | | word_freq_over <= 0.07 : 1 (8.0/1.3) | | | | | | | | | | word_freq_over > 0.07 : 0 (4.0/2.2) | | | | | | word_freq_free > 0.1 : | | | | | | | word_freq_george > 0 : 0 (32.0/1.4) | | | | | | | word_freq_george <= 0 : | | | | | | | | word_freq_people > 0.17 : 0 (20.0/1.3) | | | | | | | | word_freq_people <= 0.17 : | | | | | | | | | word_freq_our <= 1.13 : | | | | | | | | | | word_freq_85 > 0.06 : 0 (8.0/1.3) | | | | | | | | | | word_freq_85 <= 0.06 : | | | | | | | | | | | word_freq_650 > 0.13 : 1 (8.0/2.4) | | | | | | | | | | | word_freq_650 <= 0.13 : | | | | | | | | | | | | word_freq_cs > 0.08 : 0 (7.0/1.3) | | | | | | | | | | | | word_freq_cs <= 0.08 : | | | | | | | | | | | | | word_freq_pm > 0.04 : 0 (8.0/1.3) | | | | | | | | | | | | | word_freq_pm <= 0.04 :[S5] | | | | | | | | | word_freq_our > 1.13 : | | | | | | | | | | word_freq_meeting > 0.71 : 0 (2.0/1.0) | | | | | | | | | | word_freq_meeting <= 0.71 : | | | | | | | | | | | char_freq_! <= 0.279 : 1 (23.0/1.3) | | | | | | | | | | | char_freq_! > 0.279 : 0 (2.0/1.0) | | | | | word_freq_font > 0.12 : | | | | | | char_freq_; > 0.895 : 0 (15.0/1.3) | | | | | | char_freq_; <= 0.895 : | | | | | | | word_freq_edu <= 0.09 : 1 (19.0/1.3) | | | | | | | word_freq_edu > 0.09 : 0 (5.0/1.2) | | | | word_freq_money > 0.03 : | | | | | word_freq_hp > 0.08 : 0 (12.0/1.3) | | | | | word_freq_hp <= 0.08 : | | | | | | word_freq_edu > 0.08 : 0 (9.0/1.3) | | | | | | word_freq_edu <= 0.08 : | | | | | | | word_freq_project > 0.18 : 0 (4.0/1.2) | | | | | | | word_freq_project <= 0.18 : | | | | | | | | capital_run_length_longest <= 9 : 0 (5.0/2.3) | | | | | | | | capital_run_length_longest > 9 : 1 (27.0/2.6) | | | char_freq_! > 0.378 : | | | | capital_run_length_total <= 64 : | | | | | word_freq_free > 0.77 : 1 (19.0/2.5) | | | | | word_freq_free <= 0.77 : | | | | | | word_freq_george > 0.58 : 0 (10.0/1.3) | | | | | | word_freq_george <= 0.58 : | | | | | | | word_freq_business > 0.27 : 1 (7.0/2.4) | | | | | | | word_freq_business <= 0.27 : | | | | | | | | word_freq_money <= 0.23 : | | | | | | | | | word_freq_re > 0.34 : 0 (27.0/1.4) | | | | | | | | | word_freq_re <= 0.34 : | | | | | | | | | | char_freq_! <= 0.983 :[S6] | | | | | | | | | | char_freq_! > 0.983 : | | | | | | | | | | | word_freq_you <= 0.65 : 0 (15.0/3.7) | | | | | | | | | | | word_freq_you > 0.65 : 1 (13.0/2.5) | | | | | | | | word_freq_money > 0.23 : | | | | | | | | | char_freq_! <= 0.511 : 0 (3.0/1.1) | | | | | | | | | char_freq_! > 0.511 : 1 (4.0/1.2) | | | | capital_run_length_total > 64 : | | | | | char_freq_( <= 0.164 : | | | | | | char_freq_! <= 2.362 : 1 (117.0/5.0) | | | | | | char_freq_! > 2.362 : | | | | | | | capital_run_length_total <= 80 : 0 (2.0/1.0) | | | | | | | capital_run_length_total > 80 : 1 (5.0/2.3) | | | | | char_freq_( > 0.164 : | | | | | | word_freq_hp > 0.22 : 0 (5.0/1.2) | | | | | | word_freq_hp <= 0.22 : | | | | | | | word_freq_meeting > 0.09 : 0 (2.0/1.0) | | | | | | | word_freq_meeting <= 0.09 : | | | | | | | | word_freq_edu > 0.06 : 0 (2.0/1.0) | | | | | | | | word_freq_edu <= 0.06 : | | | | | | | | | char_freq_! > 0.68 : 1 (17.0/1.3) | | | | | | | | | char_freq_! <= 0.68 : | | | | | | | | | | word_freq_our > 0.08 : 1 (10.0/2.4) | | | | | | | | | | word_freq_our <= 0.08 : | | | | | | | | | | | char_freq_[ <= 0.042 : 0 (5.0/1.2) | | | | | | | | | | | char_freq_[ > 0.042 : 1 (2.0/1.0) | | word_freq_000 > 0.25 : | | | char_freq_( > 0.6 : 0 (3.0/1.1) | | | char_freq_( <= 0.6 : | | | | word_freq_hp > 0.67 : 0 (3.0/2.1) | | | | word_freq_hp <= 0.67 : | | | | | word_freq_our <= 0.83 : 1 (43.0/2.6) | | | | | word_freq_our > 0.83 : | | | | | | word_freq_you <= 1.79 : 0 (2.0/1.0) | | | | | | word_freq_you > 1.79 : 1 (3.0/1.1) | char_freq_$ > 0.055 : | | word_freq_hp > 0.39 : 0 (60.0/2.6) | | word_freq_hp <= 0.39 : | | | word_freq_edu <= 0.04 : | | | | capital_run_length_longest <= 9 : | | | | | word_freq_email > 1.43 : 1 (5.0/1.2) | | | | | word_freq_email <= 1.43 : | | | | | | capital_run_length_average <= 2.053 : 0 (18.0/1.3) | | | | | | capital_run_length_average > 2.053 : 1 (3.0/1.1) | | | | capital_run_length_longest > 9 : | | | | | char_freq_! > 0.377 : 1 (224.0/1.4) | | | | | char_freq_! <= 0.377 : | | | | | | word_freq_1999 <= 0 : 1 (242.0/15.1) | | | | | | word_freq_1999 > 0 : | | | | | | | word_freq_conference > 0.32 : 0 (2.0/1.0) | | | | | | | word_freq_conference <= 0.32 : | | | | | | | | word_freq_order > 0.41 : 0 (2.0/1.0) | | | | | | | | word_freq_order <= 0.41 : | | | | | | | | | word_freq_free <= 0.61 : 1 (7.0/1.3) | | | | | | | | | word_freq_free > 0.61 : 0 (2.0/1.0) | | | word_freq_edu > 0.04 : | | | | word_freq_addresses > 0.08 : 1 (5.0/1.2) | | | | word_freq_addresses <= 0.08 : | | | | | char_freq_; <= 0.151 : 0 (18.0/1.3) | | | | | char_freq_; > 0.151 : 1 (2.0/1.0) word_freq_remove > 0 : | word_freq_hp <= 0.19 : | | word_freq_1999 <= 0.22 : 1 (657.0/21.7) | | word_freq_1999 > 0.22 : | | | word_freq_george > 0.08 : 0 (3.0/1.1) | | | word_freq_george <= 0.08 : | | | | char_freq_; <= 0.008 : 1 (29.0/1.4) | | | | char_freq_; > 0.008 : | | | | | word_freq_our <= 0.22 : 0 (2.0/1.0) | | | | | word_freq_our > 0.22 : 1 (2.0/1.0) | word_freq_hp > 0.19 : | | char_freq_$ <= 0.028 : 0 (14.0/1.3) | | char_freq_$ > 0.028 : 1 (12.0/3.6) Subtree [S1] capital_run_length_average <= 2.674 : | capital_run_length_longest <= 21 : 0 (693.0/28.1) | capital_run_length_longest > 21 : | | word_freq_650 > 0.32 : 1 (3.0/1.1) | | word_freq_650 <= 0.32 : | | | word_freq_order <= 0.29 : 0 (33.0/3.8) | | | word_freq_order > 0.29 : 1 (2.0/1.0) capital_run_length_average > 2.674 : | word_freq_edu > 0.26 : 0 (48.0/2.6) | word_freq_edu <= 0.26 : | | word_freq_receive > 0.99 : 0 (10.0/1.3) | | word_freq_receive <= 0.99 : | | | word_freq_85 > 0.04 : 0 (4.0/1.2) | | | word_freq_85 <= 0.04 : | | | | word_freq_conference > 0.37 : 0 (4.0/1.2) | | | | word_freq_conference <= 0.37 : | | | | | word_freq_project > 0.41 : 0 (4.0/1.2) | | | | | word_freq_project <= 0.41 : | | | | | | char_freq_# > 0.011 : 0 (3.0/1.1) | | | | | | char_freq_# <= 0.011 : | | | | | | | word_freq_re > 1.06 : 0 (3.0/1.1) | | | | | | | word_freq_re <= 1.06 : | | | | | | | | word_freq_meeting > 0.22 : 0 (4.0/1.2) | | | | | | | | word_freq_meeting <= 0.22 : | | | | | | | | | word_freq_pm > 0.24 : 0 (5.0/1.2) | | | | | | | | | word_freq_pm <= 0.24 : | | | | | | | | | | capital_run_length_total <= 30 : 0 (12.0/2.5) | | | | | | | | | | capital_run_length_total > 30 : 1 (34.0/12.4) Subtree [S2] word_freq_lab > 0.01 : 0 (2.0/1.0) word_freq_lab <= 0.01 : | word_freq_all > 0.74 : 0 (2.0/1.0) | word_freq_all <= 0.74 : | | capital_run_length_longest <= 5 : 0 (2.0/1.0) | | capital_run_length_longest > 5 : 1 (7.0/1.3) Subtree [S3] word_freq_650 > 0.74 : 1 (2.0/1.0) word_freq_650 <= 0.74 : | word_freq_over > 0.3 : 1 (2.0/1.0) | word_freq_over <= 0.3 : | | word_freq_address <= 0.56 : 0 (20.0/1.3) | | word_freq_address > 0.56 : 1 (2.0/1.0) Subtree [S4] capital_run_length_longest <= 10 : 0 (71.0/5.0) capital_run_length_longest > 10 : | word_freq_hp > 0.11 : 0 (20.0/1.3) | word_freq_hp <= 0.11 : | | word_freq_re > 0.16 : 0 (2.0/1.0) | | word_freq_re <= 0.16 : | | | char_freq_! <= 0.112 : 1 (6.0/1.2) | | | char_freq_! > 0.112 : 0 (3.0/2.1) Subtree [S5] word_freq_make > 0.21 : 0 (11.0/1.3) word_freq_make <= 0.21 : | capital_run_length_longest <= 42 : | | word_freq_meeting > 0.4 : 0 (5.0/1.2) | | word_freq_meeting <= 0.4 : | | | word_freq_project > 0.4 : 0 (5.0/1.2) | | | word_freq_project <= 0.4 : | | | | word_freq_hp > 1.36 : 0 (4.0/1.2) | | | | word_freq_hp <= 1.36 : | | | | | word_freq_telnet > 0.13 : 0 (2.0/1.0) | | | | | word_freq_telnet <= 0.13 : | | | | | | capital_run_length_average <= 1.292 : 0 (11.0/4.6) | | | | | | capital_run_length_average > 1.292 : 1 (40.0/9.4) | capital_run_length_longest > 42 : | | word_freq_mail <= 0.47 : 0 (29.0/1.4) | | word_freq_mail > 0.47 : 1 (4.0/1.2) Subtree [S6] capital_run_length_total <= 48 : 0 (67.0/6.1) capital_run_length_total > 48 : 1 (5.0/3.2) Tree saved Evaluation on training data (4142 items): Before Pruning After Pruning ---------------- --------------------------- Size Errors Size Errors Estimate 361 73( 1.8%) 219 114( 2.8%) ( 6.3%) <<