Titanic

library(dyplr)

Error in library(dyplr) : there is no package called ‘dyplr’

glimpse(train)

Observations: 891
Variables: 12
$ PassengerId <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1...
$ Survived    <dbl> 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, ...
$ Pclass      <dbl> 3, 1, 3, 1, 3, 3, 1, 3, 3, 2, 3, 1, 3, 3, 3, 2, 3, 2, 3, 3, ...
$ Name        <chr> "Braund, Mr. Owen Harris", "Cumings, Mrs. John Bradley (Flor...
$ Sex         <chr> "male", "female", "female", "female", "male", "male", "male"...
$ Age         <dbl> 22, 38, 26, 35, 35, NA, 54, 2, 27, 14, 4, 58, 20, 39, 14, 55...
$ SibSp       <dbl> 1, 1, 0, 1, 0, 0, 0, 3, 0, 1, 1, 0, 0, 1, 0, 0, 4, 0, 1, 0, ...
$ Parch       <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 2, 0, 1, 0, 0, 5, 0, 0, 1, 0, 0, 0, ...
$ Ticket      <chr> "A/5 21171", "PC 17599", "STON/O2. 3101282", "113803", "3734...
$ Fare        <dbl> 7.2500, 71.2833, 7.9250, 53.1000, 8.0500, 8.4583, 51.8625, 2...
$ Cabin       <chr> NA, "C85", NA, "C123", NA, NA, "E46", NA, NA, NA, "G6", "C10...
$ Embarked    <chr> "S", "C", "S", "S", "S", "Q", "S", "S", "S", "C", "S", "S", ...

Modelo 1

train%>% 
  group_by(Sex, Survived)%>%
  summarise(n=n())

test%>%
    mutate(Survived = if_else(Sex == "male",0,1))%>%
  dplyr:: select(PassengerId, Survived)%>%
  write.csv("modelo1.csv")

Error in test %>% mutate(Survived = if_else(Sex == "male", 0, 1)) %>%  : 
  could not find function "%>%"

Modelo 2 (Regresion logistica)

train$Age <- ifelse(is.na(train$Age), 27,train$Age )
test$Age <- ifelse(is.na(test$Age), 27,test$Age )
fit_logit <- glm(Survived ~ Pclass + Sex + Embarked + Age, data = train, family = "binomial")
summary(fit_logit)

Call:
glm(formula = Survived ~ Pclass + Sex + Embarked + Age, family = "binomial", 
    data = train)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-2.5816  -0.6339  -0.4111   0.6620   2.4794  

Coefficients:
             Estimate Std. Error z value Pr(>|z|)    
(Intercept)  5.022981   0.473616  10.606  < 2e-16 ***
Pclass      -1.158200   0.125167  -9.253  < 2e-16 ***
Sexmale     -2.576963   0.187622 -13.735  < 2e-16 ***
EmbarkedQ   -0.028847   0.368034  -0.078   0.9375    
EmbarkedS   -0.502394   0.229325  -2.191   0.0285 *  
Age         -0.033231   0.007428  -4.474 7.68e-06 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 1182.82  on 888  degrees of freedom
Residual deviance:  798.78  on 883  degrees of freedom
  (2 observations deleted due to missingness)
AIC: 810.78

Number of Fisher Scoring iterations: 5

fit_logit_predict <- predict(fit_logit, test, type = "response")
fit_logit_predict

         1          2          3          4          5          6          7 
0.09940087 0.37381817 0.12351548 0.08104644 0.57808191 0.11960143 0.62775620 
         8          9         10         11         12         13         14 
0.22499658 0.72115986 0.09719150 0.08104644 0.32230418 0.93073748 0.07825252 
        15         16         17         18         19         20         21 
0.85821329 0.87091081 0.25686734 0.15104435 0.53711890 0.51324302 0.36821357 
        22         23         24         25         26         27         28 
0.13823174 0.92166225 0.64335748 0.90633560 0.03944792 0.95826156 0.14476309 
        29         30         31         32         33         34         35 
0.35961221 0.12721401 0.11564567 0.23679711 0.48734348 0.53711890 0.57221336 
        36         37         38         39         40         41         42 
0.16200894 0.53711890 0.58616535 0.08613624 0.08104644 0.08910664 0.47207577 
        43         44         45         46         47         48         49 
0.05247842 0.76981310 0.86610971 0.08613624 0.44829103 0.12404540 0.86656459 
        50         51         52         53         54         55         56 
0.46248812 0.49696999 0.31699426 0.82340169 0.91922907 0.31699426 0.19944940 
        57         58         59         60         61         62         63 
0.06332468 0.08613624 0.08104644 0.93513992 0.10949566 0.19213939 0.10629723 
        64         65         66         67         68         69         70 
0.68749865 0.70178551 0.78700221 0.71532222 0.31508899 0.56406008 0.79714181 
        71         72         73         74         75         76         77 
0.67304486 0.09719150 0.52056020 0.58436878 0.93712658 0.55176629 0.08104644 
        78         79         80         81         82         83         84 
0.82269010 0.20266729 0.67304486 0.22653726 0.19138213 0.30092524 0.08104644 
        85         86         87         88         89         90         91 
0.31078185 0.12721401 0.65074054 0.61012281 0.65074054 0.39192264 0.57808191 
        92         93         94         95         96         97         98 
0.08104644 0.92166225 0.08104644 0.61231234 0.08613624 0.69779695 0.07623230 
        99        100        101        102        103        104        105 
0.59420263 0.06738315 0.91952026 0.21925498 0.12404540 0.08355612 0.73432623 
       106        107        108        109        110        111        112 
0.07860566 0.14738241 0.12404540 0.08104644 0.27139636 0.22568231 0.65074054 
       113        114        115        116        117        118        119 
0.93513992 0.71192663 0.78054280 0.16427739 0.12721401 0.73355914 0.52285935 
       120        121        122        123        124        125        126 
0.77564881 0.85880678 0.12404540 0.93712658 0.07860566 0.12404540 0.61799803 
       127        128        129        130        131        132        133 
0.09431441 0.65074054 0.14573162 0.08878831 0.06950174 0.38380562 0.53711890 
       134        135        136        137        138        139        140 
0.12721401 0.04927023 0.08878831 0.12907030 0.22499658 0.56995642 0.05415560 
       141        142        143        144        145        146        147 
0.67121307 0.90600158 0.32316282 0.21361951 0.35199563 0.07168182 0.47207577 
       148        149        150        151        152        153        154 
0.09431441 0.47207577 0.20266729 0.95691201 0.12721401 0.02815551 0.46248812 
       155        156        157        158        159        160        161 
0.12314502 0.08878831 0.91672714 0.56995642 0.35199563 0.54536993 0.65074054 
       162        163        164        165        166        167        168 
0.22076755 0.79251959 0.08104644 0.14991758 0.54536993 0.42378097 0.10629723 
       169        170        171        172        173        174        175 
0.95108610 0.57808191 0.08104644 0.12721401 0.09151386 0.12721401 0.05415560 
       176        177        178        179        180        181        182 
0.84628053 0.82340169 0.37597746 0.73260310 0.85043222 0.20266729 0.51456342 
       183        184        185        186        187        188        189 
0.94071191 0.12404540 0.95108610 0.15420206 0.81851748 0.10949566 0.53711890 
       190        191        192        193        194        195        196 
0.15420206 0.18203353 0.47207577 0.12862935 0.12715829 0.34555770 0.06738315 
       197        198        199        200        201        202        203 
0.74808634 0.61012281 0.24285519 0.53711890 0.65074054 0.17625317 0.43191553 
       204        205        206        207        208        209        210 
0.87416953 0.23084407 0.59642242 0.58818025 0.23679711 0.94093063 0.08613624 
       211        212        213        214        215        216        217 
0.06950174 0.08104644 0.28136455 0.55238837 0.44601327 0.35199563 0.65074054 
       218        219        220        221        222        223        224 
0.24810511 0.90053914 0.08104644 0.84679087 0.09719150 0.81352878 0.09719150 
       225        226        227        228        229        230        231 
0.89124641 0.65726798 0.09151386 0.65074054 0.05331079 0.17234580 0.30195408 
       232        233        234        235        236        237        238 
0.93490124 0.09719150 0.12404540 0.49795204 0.10014666 0.30175228 0.15535516 
       239        240        241        242        243        244        245 
0.83285927 0.90633560 0.88463501 0.67013391 0.44829103 0.08104644 0.08104644 
       246        247        248        249        250        251        252 
0.35961221 0.81352878 0.14573162 0.77564881 0.65726798 0.89785493 0.10014666 
       253        254        255        256        257        258        259 
0.59642242 0.08878831 0.06843485 0.08104644 0.12404540 0.07860566 0.82818205 
       260        261        262        263        264        265        266 
0.09719150 0.06043162 0.09719150 0.77564881 0.73355914 0.29581379 0.08104644 
       267        268        269        270        271        272        273 
0.47207577 0.08104644 0.53711890 0.10949566 0.44008698 0.12404540 0.95260908 
       274        275        276        277        278        279        280 
0.65074054 0.12721401 0.82340169 0.21361951 0.15420206 0.20266729 0.24901769 
       281        282        283        284        285        286        287 
0.56995642 0.17423592 0.65074054 0.77717891 0.72701394 0.06138197 0.08104644 
       288        289        290        291        292        293        294 
0.49696999 0.12721401 0.08104644 0.47207577 0.62775620 0.12721401 0.27372198 
       295        296        297        298        299        300        301 
0.06138197 0.08355612 0.93543563 0.12721401 0.44731965 0.07623230 0.06950174 
       302        303        304        305        306        307        308 
0.31699426 0.14164307 0.08878831 0.65074054 0.77479743 0.44731965 0.17385376 
       309        310        311        312        313        314        315 
0.26070992 0.38950124 0.10629723 0.14683237 0.08104644 0.57199262 0.88463501 
       316        317        318        319        320        321        322 
0.72204058 0.35289218 0.26812331 0.08104644 0.24901769 0.08355612 0.13477795 
       323        324        325        326        327        328        329 
0.22499658 0.42282200 0.88759199 0.09151386 0.85880678 0.44008698 0.20809028 
       330        331        332        333        334        335        336 
0.25528384 0.64773495 0.49795204 0.12721401 0.71442864 0.08104644 0.44731965 
       337        338        339        340        341        342        343 
0.19213939 0.08910664 0.23084407 0.12721401 0.27469436 0.06950174 0.08104644 
       344        345        346        347        348        349        350 
0.87406416 0.08104644 0.62581174 0.22499658 0.57091901 0.23679711 0.76387181 
       351        352        353        354        355        356        357 
0.91446273 0.23084407 0.27469436 0.11908791 0.73891516 0.29398103 0.80246246 
       358        359        360        361        362        363        364 
0.08104644 0.12404540 0.51226158 0.11786289 0.87091081 0.76387181 0.08104644 
       365        366        367        368        369        370        371 
0.95408693 0.53711890 0.12721401 0.57808191 0.91446273 0.30278272 0.25528384 
       372        373        374        375        376        377        378 
0.94451815 0.30092524 0.13765074 0.82748568 0.91446273 0.57808191 0.25528384 
       379        380        381        382        383        384        385 
0.26070992 0.15484038 0.12404540 0.12770156 0.53711890 0.60218975 0.21925498 
       386        387        388        389        390        391        392 
0.80323581 0.08878831 0.09389789 0.14738241 0.15054131 0.50527751 0.84125620 
       393        394        395        396        397        398        399 
0.12314502 0.12623857 0.07623230 0.94071191 0.13529000 0.90633560 0.09431441 
       400        401        402        403        404        405        406 
0.11030880 0.91415495 0.16307086 0.95826156 0.55490199 0.46477943 0.36935092 
       407        408        409        410        411        412        413 
0.24285519 0.40763927 0.65074054 0.72036924 0.65074054 0.93127142 0.52884748 
       414        415        416        417        418 
0.08104644 0.92882447 0.05676636 0.08104644 0.12721401 

Survived <- ifelse(fit_logit_predict > 0.7, 1, 0)
cbind(test, Survived)%>%
    dplyr::select(PassengerId, Survived)%>%
    write.csv("modelo5.csv")