CSX_R Project 3

my site: https://b04902122.github.io/CSX_R/project_3/titanic.html

Import libraries

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(rpart)
library(rpart.plot)

Read data

MyData <- read.csv(file="/Users/ymc/Desktop/titanicTrain.csv", header=TRUE, sep=",", stringsAsFactors = FALSE)
MyPred <- read.csv(file="/Users/ymc/Desktop/titanicQuestion.csv", header=TRUE, sep=",", stringsAsFactors = FALSE)
total=nrow(MyData)
total1=nrow(MyPred)
t_age=0

Clean my train data

Remove unnecessary column

Change col.boat data to 0 & 1

Fill NA age with average age

for (i in 1:nrow(MyData))
  if(is.na(MyData$age[i]) || MyData$age[i]<1){
    total <- total - 1
  } else {
    t_age <- t_age + MyData$age[i]
  }
avage <- t_age/total

for (i in 1:nrow(MyData))
  if(is.na(MyData$age[i]) || MyData$age[i]<1){
    MyData$age[i] <- 31.44
  }

for (i in 1:nrow(MyData))
  if(MyData$boat[i] == ''){
    MyData$boat[i] <- NA
  } else {
    MyData$boat[i] <- 1
  }

for (i in 1:nrow(MyData))
  if(is.na(MyData$boat[i])){
    MyData$boat[i] <- 0
  } 

Clean my test data

Remove unnecessary column

Change col.boat data to 0 & 1

Fill NA age with average age

for (i in 1:nrow(MyPred))
  if(is.na(MyPred$age[i]) || MyPred$age[i]<1){
    MyPred$age[i] <- 31.44
  }

for (i in 1:nrow(MyPred))
  if(MyPred$boat[i] == ''){
    MyPred$boat[i] <- NA
  } else {
    MyPred$boat[i] <- 1
  }

for (i in 1:nrow(MyPred))
  if(is.na(MyPred$boat[i])){
    MyPred$boat[i] <- 0
  } 

Write train & test data

write.csv(MyData, file="MyData1.csv")
write.csv(MyPred, file="MyPred1.csv")

Use python to train data

#import pandas as pd
#from sklearn.tree import DecisionTreeRegressor
#train = pd.read_csv('/Users/ymc/Desktop/MyData2.csv')
#test = pd.read_csv('/Users/ymc/Desktop/MyPred2.csv')

##factors that will predict the price
#desired_factors = ['boat']

##set my model to DecisionTree
#model = DecisionTreeRegressor()

##set prediction data to factors that will predict, and set target to SalePrice
#train_data = train[desired_factors]
#test_data = test[desired_factors]
#target = train.survived

##fitting model with prediction data and telling it my target
#model.fit(train_data, target)
#res = model.predict(test_data)

##write predicted data
#with open('/Users/ymc/Desktop/result2.csv','a') as file:
#    for i in range(len(res)):
#        if(res[i]>0.5):
#            file.write('1')
#            file.write("\n")
#        else:
#            file.write('0')
#            file.write("\n")