HelloDATA1/SQLiteArrowKit.jl at main · Uriel1201/HelloDATA1 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
module SQLiteArrowKit

using DataFrames, Arrow, SQLite, CSV, DuckDB

export is_available, get_ArrowTable, get_DataFrame

const DB_PATH = "/content/popular.db"
#=
**********************************************
=#
function is_available(db::SQLite.DB, table::String)::Bool

    name = uppercase(table)
    list_tables = collect(SQLite.tables(db))
    names = [t.name for t in list_tables]

    return name in names

end
#=
**********************************************
=#
function get_ArrowTable(db::SQLite.DB, table::String)::Arrow.Table

    name = uppercase(table)
    io = IOBuffer()
    cursor = DBInterface.execute(db, "SELECT * FROM $name")
    Arrow.write(io, cursor)
    seekstart(io)
    arrow_table = Arrow.Table(io)

    return arrow_table

end
#=
**********************************************
=#
function get_DataFrame(db::SQLite.DB, table::String)::DataFrame

    name = uppercase(table)

    return DBInterface.execute(db, "SELECT * FROM $name") |> DataFrame

end
#=
**********************************************
THIS FUNCTION IS ONLY A TEST AND IT MUSTN'T BE EXECUTED
=#
function main(csv_path::String, db_table::String)

    println("DATA SIZE~437 MB")
    println("\n", "*"^40)

    db = SQLite.DB(DB_PATH)

    csvstart = time()
    songs_csv = CSV.read(csv_path, DataFrame; header = true, delim = ',')
    csvend = time()
    lecture_csv = round(csvend - csvstart, digits = 4)
    println("LECTURE TIME, FROM CSV TO DATAFRAMES: $lecture_csv")
    println("PROCESSING TIME, USING DATAFRAMES:")

    start_df = time()
    dfMode = combine(groupby(songs_csv,
                             "mode"
                     ),
                     nrow => :frequency
             )
    dfModePopularity = combine(groupby(filter(:popularity => x -> x > 95,
                                       songs_csv
                                       ),
                                       [:spotify_id,
                                        :name,
                                        :mode]
                               ),
                               nrow => :persistenceInPopularity
                       )
    result= first(filter(:persistenceInPopularity => x -> x > 5000, dfModePopularity), 10)

    end_df = time()
    elap_df = round(end_df - start_df, digits = 4)
    println("\n$dfMode")
    println("\n$result\n")
    println("\ntime~$elap_df")

    if is_available(db, db_table)

            duck = nothing

            try

                duck = DBInterface.connect(DuckDB.DB, ":memory:")

                println("\n", "*"^40)

                arrow_start = time()
                duck_songs = get_ArrowTable(db, db_table)
                arrow_end = time()
                elap_arrow = round(arrow_end - arrow_start, digits = 4)
                println("LECTURE TIME (EXPLICIT EXPORT), FROM CURSOR TO ARROW TABLE:\n$elap_arrow")

                duck_start = time()
                DuckDB.register_data_frame(duck, duck_songs, "SONGS")
                mode =  """
                        SELECT
                            mode,
                            COUNT(*) AS frequency
                        FROM
                            SONGS
                        GROUP BY
                            mode
                """
                modePopularity = """
                                 WITH
                                     POPULAR AS(
                                         SELECT
                                             name,
                                             mode,
                                             COUNT(*) AS persistenceInPopularity95
                                         FROM
                                             SONGS
                                         WHERE
                                             popularity > 95
                                         GROUP BY
                                             spotify_id, name, mode)
                                 SELECT
                                     *
                                 FROM
                                     POPULAR
                                 WHERE
                                     persistenceInPopularity95 > 5000
                """
                modeDuck = DBInterface.execute(duck, mode) |> DataFrame
                popularityDuck = DBInterface.execute(duck, modePopularity) |> DataFrame
                duck_end = time()
                elap_duck = round(duck_end - duck_start, digits = 4)

                println("PROCESSING TIME, USING DUCKDB QUERIES: $elap_duck")
                println("\n$modeDuck")
                println("\n$popularityDuck")

            finally

                DBInterface.close!(duck)

            end

        end

end
#=
**********************************************
=#
end
#=
**********************************************
=#
if Base.@isdefined(PROGRAM_FILE) &&
   abspath(PROGRAM_FILE) == abspath(@__FILE__)

    a = ARGS[1]
    b = ARGS[2]
    main(a, b)

end