Titanic docs added (#92)

Author: arcAman07

README.md

@@ -31,6 +31,7 @@ Find below a list of available datasets and links to their documentation.
   - [BostonHousing](https://juliaml.github.io/MLDatasets.jl/dev/datasets/BostonHousing/)
   - [Iris](https://juliaml.github.io/MLDatasets.jl/dev/datasets/Iris/)
   - [Mutagenesis](https://relational.fit.cvut.cz/dataset/Mutagenesis)
+  - [Titanic](https://juliaml.github.io/MLDatasets.jl/dev/datasets/Titanic/)
 
 #### Text
   - [PTBLM](https://juliaml.github.io/MLDatasets.jl/dev/datasets/PTBLM/)

docs/make.jl

@@ -35,6 +35,7 @@ makedocs(
                 "Iris" => "datasets/Iris.md",
                 "Boston Housing" => "datasets/BostonHousing.md",
                 "Mutagenesis" => "datasets/Mutagenesis.md",
+                "Titanic" => "datasets/Titanic.md",
             ],
 
             "Text" => Any[

docs/src/datasets/Titanic.md

@@ -0,0 +1,13 @@
+# Titanic
+
+```@docs
+Titanic
+```
+
+## API reference
+
+```@docs
+Titanic.feature_names
+Titanic.features
+Titanic.targets
+```

src/Titanic/Titanic.jl

@@ -1,6 +1,7 @@
 export Titanic
+
 """
-Titanic Dataset
+Titanic Dataset.
 
 The titanic and titanic2 data frames describe the survival status of individual passengers on the Titanic. 
 
@@ -24,12 +25,6 @@ using the Encyclopedia Titanica and created a new dataset called titanic3.
 These datasets reflects the state of data available as of 2 August 1999. 
 Some duplicate passengers have been dropped, many errors corrected, many missing ages filled in, and new variables created.
 
-# Interface
-
-- [`Titanic.features`](@ref)
-- [`Titanic.targets`](@ref)
-- [`Titanic.feature_names`](@ref)
-
 DATASET specs
 
 NAME:	titanic3
@@ -63,8 +58,6 @@ body	Body Identification Number
 home.dest	Home/Destination
 
 
-
-
 SPECIAL NOTES
 
 Pclass is a proxy for socio-economic status (SES) 1st ~ Upper; 2nd ~ Middle; 3rd ~ Lower
@@ -94,6 +87,12 @@ attach	(titanic3)
 plsmo	(age, survived, group=sex, datadensity=T) 
 # or group=pclass plot	(naclus	(titanic3)) # study patterns of missing values summary	(survived ~ age + sex + pclass + sibsp + parch, data=titanic3)
 
+
+# Interface
+
+- [`Titanic.features`](@ref)
+- [`Titanic.targets`](@ref)
+- [`Titanic.feature_names`](@ref)
 """
 module Titanic
 
@@ -116,45 +115,45 @@ julia> using MLDatasets: Titanic
 julia> target = Titanic.targets();
 
 julia> summary(target)
-"1×891 Matrix{Float64}"
-     
-"""
+"1×891 Matrix{Any}"
 
+julia> target[1]
+0
+```
+"""
 function targets(; dir = nothing)
     titanic_data = readdlm(DATA, ',')
-    reshape(Vector(titanic_data[2:end,2]), (1, 891))
+    reshape(Vector(titanic_data[2:end, 2]), (1, 891))
 end
 
 """
     feature_names()
 
 Return the  the names of the features provided in the dataset.
 """
-
 function feature_names()
     ["PassengerId", "Pclass", "Name", "Sex", "Age", "SibSp", "Parch", "Ticket", "Fare", "Cabin", "Embarked"]
 end
 
 """
     features()
 
-Return the features of the Boston Housing dataset. This is a 13x506 Matrix of Float64 datatypes.
-The values are in the order ["crim","zn","indus","chas","nox","rm","age","dis","rad","tax","ptratio","b","lstat"].
-It has 506 examples.
+Return the features of the Titanic dataset. This is a 11x891 Matrix of containing both String and Float datatypes.
+The values are in the order ["PassengerId", "Pclass", "Name", "Sex", "Age", "SibSp", "Parch", "Ticket", "Fare", "Cabin", "Embarked"].
+It has 891 examples.
 
 ```jldoctest
-julia> using MLDatasets: BostonHousing
+julia> using MLDatasets: Titanic
 
-julia> features = BostonHousing.features();
+julia> features = Titanic.features();
 
 julia> summary(features)
-"13×506 Matrix{Float64}"
+"11×891 Matrix{Any}"
 ```
 """
-
 function features()
     titanic_data = readdlm(DATA, ',')
-    reshape(Matrix(hcat(titanic_data[2:end, 1], titanic_data[2:end, 3:12])),(11,891))
+    reshape(Matrix(hcat(titanic_data[2:end, 1], titanic_data[2:end, 3:12])), (11, 891))
 end
 
 end # module