update CSV to 0.8

Author: MegamindHenry

Manifest.toml

@@ -16,10 +16,10 @@ uuid = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
 version = "0.5.0"
 
 [[CSV]]
-deps = ["CategoricalArrays", "DataFrames", "Dates", "Mmap", "Parsers", "PooledArrays", "SentinelArrays", "Tables", "Unicode"]
-git-tree-sha1 = "b1f60ea404dc40a76e7f539672ce651079a5a190"
+deps = ["Dates", "Mmap", "Parsers", "PooledArrays", "SentinelArrays", "Tables", "Unicode"]
+git-tree-sha1 = "1f79803452adf73e2d3fc84785adb7aaca14db36"
 uuid = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
-version = "0.7.10"
+version = "0.8.3"
 
 [[CategoricalArrays]]
 deps = ["DataAPI", "Future", "JSON", "Missings", "Printf", "Statistics", "StructTypes", "Unicode"]
@@ -87,9 +87,9 @@ uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
 
 [[Distributions]]
 deps = ["FillArrays", "LinearAlgebra", "PDMats", "Printf", "QuadGK", "Random", "SparseArrays", "SpecialFunctions", "Statistics", "StatsBase", "StatsFuns"]
-git-tree-sha1 = "5a9a742ae30f13d6172c7ea245988d932134e25b"
+git-tree-sha1 = "0fc424e725eaec6ea3e9fa8df773bee18a1ab503"
 uuid = "31c24e10-a181-5473-b8eb-7969acd0382f"
-version = "0.24.13"
+version = "0.24.14"
 
 [[DocStringExtensions]]
 deps = ["LibGit2", "Markdown", "Pkg", "Test"]
@@ -111,9 +111,9 @@ version = "0.2.0"
 
 [[FillArrays]]
 deps = ["LinearAlgebra", "Random", "SparseArrays"]
-git-tree-sha1 = "e384d3cff80ac79c7a541a817192841836e46331"
+git-tree-sha1 = "4705cc4e212c3c978c60b1b18118ec49b4d731fd"
 uuid = "1a297f60-69ca-5386-bcde-b61e274b549b"
-version = "0.11.2"
+version = "0.11.5"
 
 [[Future]]
 deps = ["Random"]
@@ -197,9 +197,9 @@ uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
 version = "0.5.3+4"
 
 [[OrderedCollections]]
-git-tree-sha1 = "d45739abcfc03b51f6a42712894a593f74c80a23"
+git-tree-sha1 = "4fa2ba51070ec13fcc7517db714445b4ab986bdf"
 uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
-version = "1.3.3"
+version = "1.4.0"
 
 [[PDMats]]
 deps = ["LinearAlgebra", "SparseArrays", "SuiteSparse", "Test"]
@@ -302,25 +302,19 @@ uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 
 [[SpecialFunctions]]
 deps = ["ChainRulesCore", "OpenSpecFun_jll"]
-git-tree-sha1 = "75394dbe2bd346beeed750fb02baa6445487b862"
+git-tree-sha1 = "5919936c0e92cff40e57d0ddf0ceb667d42e5902"
 uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
-version = "1.2.1"
-
-[[StaticArrays]]
-deps = ["LinearAlgebra", "Random", "Statistics"]
-git-tree-sha1 = "da4cf579416c81994afd6322365d00916c79b8ae"
-uuid = "90137ffa-7385-5640-81b9-e52037218182"
-version = "0.12.5"
+version = "1.3.0"
 
 [[Statistics]]
 deps = ["LinearAlgebra", "SparseArrays"]
 uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 
 [[StatsBase]]
 deps = ["DataAPI", "DataStructures", "LinearAlgebra", "Missings", "Printf", "Random", "SortingAlgorithms", "SparseArrays", "Statistics"]
-git-tree-sha1 = "7bab7d4eb46b225b35179632852b595a3162cb61"
+git-tree-sha1 = "400aa43f7de43aeccc5b2e39a76a79d262202b76"
 uuid = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
-version = "0.33.2"
+version = "0.33.3"
 
 [[StatsFuns]]
 deps = ["Rmath", "SpecialFunctions"]

docs/src/index.md

@@ -51,7 +51,7 @@ We first download and read the csv file into Julia:
 ```julia
 download("https://osf.io/2ejfu/download", "latin.csv")
 
-latin = CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "latin.csv")));
+latin = DataFrame(CSV.File(joinpath(@__DIR__, "latin.csv")));
 ```
 
 and we can inspect the latin dataframe:
@@ -347,8 +347,8 @@ The model also provides functionality for cross-validation. Here, you can downlo
 download("https://osf.io/2ejfu/download", "latin_train.csv")
 download("https://osf.io/bm7y6/download", "latin_val.csv")
 
-latin_train = CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "latin_train.csv")))
-latin_val = CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "latin_val.csv")))
+latin_train = DataFrame(CSV.File(joinpath(@__DIR__, "latin_train.csv")))
+latin_val = DataFrame(CSV.File(joinpath(@__DIR__, "latin_val.csv")))
 ```
 
 Then, we make the C and S matrices passing both training and validation datasets to the `make_cue_matrix` function.

examples/estonian.jl

@@ -3,9 +3,9 @@ using CSV # read csv files into dataframes
 
 # load estonian file
 estonian_train =
-    CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "data", "estonian_train.csv")))
+    DataFrame(CSV.File(joinpath(@__DIR__, "data", "estonian_train.csv")))
 estonian_val =
-    CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "data", "estonian_val.csv")))
+    DataFrame(CSV.File(joinpath(@__DIR__, "data", "estonian_val.csv")))
 
 # create C matrixes for training and validation datasets
 cue_obj_train = JudiLing.make_cue_matrix(

examples/latin.jl

@@ -5,7 +5,7 @@ mkpath(joinpath(@__DIR__, "data"))
 download("https://osf.io/2ejfu/download", "latin.csv")
 mv("latin.csv", joinpath(@__DIR__, "data", "latin.csv"), force = true)
 # load latin file
-latin = CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "data", "latin.csv")))
+latin = DataFrame(CSV.File(joinpath(@__DIR__, "data", "latin.csv")))
 display(latin)
 
 # create C matrixes for training datasets
@@ -171,9 +171,9 @@ mv(
 mv("latin_val.csv", joinpath(@__DIR__, "data", "latin_val.csv"), force = true)
 # cross-validation
 latin_train =
-    CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "data", "latin_train.csv")))
+    DataFrame(CSV.File(joinpath(@__DIR__, "data", "latin_train.csv")))
 latin_val =
-    CSV.DataFrame!(CSV.File(joinpath(@__DIR__, "data", "latin_val.csv")))
+    DataFrame(CSV.File(joinpath(@__DIR__, "data", "latin_val.csv")))
 
 # create C matrices for both training and validation datasets
 cue_obj_train, cue_obj_val = JudiLing.make_cue_matrix(

src/make_yt_matrix.jl

@@ -22,7 +22,7 @@ for the corresponding n-gram predicted for timestep t for each of the observatio
 
 # Examples
 ```julia
-latin = CSV.DataFrame!(CSV.File(joinpath("data", "latin_mini.csv")))
+latin = DataFrame(CSV.File(joinpath("data", "latin_mini.csv")))
 JudiLing.make_Yt_matrix(2, latin)
 ```
 ...

src/output.jl

@@ -424,7 +424,7 @@ L_load = JudiLing.load_L_matrix(joinpath(@__DIR__, "L.csv"))
 """
 function load_L_matrix(filename; header = false)
 
-    L_df = CSV.DataFrame!(CSV.File(filename, header = header))
+    L_df = DataFrame(CSV.File(filename, header = header))
     i2f = L_df[:, 1]
     f2i = Dict(v => i for (i, v) in enumerate(i2f))
     ncol = size(L_df, 2) - 1

src/preprocess.jl

@@ -24,7 +24,7 @@ Leave p out cross-validation.
 """
 function lpo_cv_split(p, data_path; random_seed = 314)
     # read csv
-    data = CSV.DataFrame!(CSV.File(data_path))
+    data = DataFrame(CSV.File(data_path))
 
     # shuffle data
     rng = MersenneTwister(random_seed)
@@ -60,7 +60,7 @@ function train_val_split(
 )
 
     # read csv
-    utterances = CSV.DataFrame!(CSV.File(data_path))
+    utterances = DataFrame(CSV.File(data_path))
 
     # shuffle data
     rng = MersenneTwister(random_seed)
@@ -160,7 +160,7 @@ function train_val_split(
 )
 
     # read csv
-    utterances = CSV.DataFrame!(CSV.File(data_path))
+    utterances = DataFrame(CSV.File(data_path))
     num_utterances = size(utterances, 1)
 
     # shuffle data
@@ -385,7 +385,7 @@ function preprocess_ndl(
 )
 
     # read csv
-    data = CSV.DataFrame!(CSV.File(data_path))
+    data = DataFrame(CSV.File(data_path))
 
     io = GZip.open(joinpath(save_path), "w")
 

src/test_combo.jl

@@ -193,11 +193,11 @@ function test_combo(
 
     # load data
     verbose && println("Loading CSV...")
-    data_train = CSV.DataFrame!(CSV.File(joinpath(
+    data_train = DataFrame(CSV.File(joinpath(
         output_dir_path,
         "$(data_prefix)_train.csv",
     )))
-    data_val = CSV.DataFrame!(CSV.File(joinpath(
+    data_val = DataFrame(CSV.File(joinpath(
         output_dir_path,
         "$(data_prefix)_val.csv",
     )))

test/cholesky_tests.jl

@@ -2,6 +2,7 @@ using JudiLing
 using CSV
 using Test
 using SparseArrays
+using DataFrames
 
 @testset "cholesky transformation matrix" begin
     try
@@ -35,7 +36,7 @@ end
 @testset "cholesky transformation matrix for latin" begin
     try
         latin_train =
-            CSV.DataFrame!(CSV.File(joinpath("data", "latin_mini.csv")))
+            DataFrame(CSV.File(joinpath("data", "latin_mini.csv")))
         cue_obj_train = JudiLing.make_cue_matrix(
             latin_train,
             grams = 3,

test/find_path_tests.jl

@@ -1,11 +1,12 @@
 using JudiLing
 using CSV
 using Test
+using DataFrames
 
 @testset "path finding for latin" begin
     try
         latin_train =
-            CSV.DataFrame!(CSV.File(joinpath("data", "latin_mini.csv")))
+            DataFrame(CSV.File(joinpath("data", "latin_mini.csv")))
         cue_obj_train = JudiLing.make_cue_matrix(
             latin_train,
             grams = 3,