lucifermorningstar1305

update_lexicon!(crps)

lucifermorningstar1305

crps = Corpus(df[:, :Message2])

lucifermorningstar1305

remove_case!.(df[:, :Message2])
prepare!.(df[:, :Message2], strip_html_tags| strip_punctuation| strip_numbers)
stem!.(df[:, :Message2])

lucifermorningstar1305

df = @chain df begin
  DataFrames.transform(:Message => ByRow(x -> StringDocument(x)) => :Message2)
end

lucifermorningstar1305

df = CSV.read("spam_dataset.csv", DataFrames.DataFrame)
first(df, 10) |> pretty

lucifermorningstar1305

using DataFrames 
using CSV
using Gadfly
using TextAnalysis
using MLJ
using Chain
using Pipe
using StableRNGs

lucifermorningstar1305

> ]
> activate .
> add IJulia BenchmarkTools Plots DataFrames CSV MLJ MLJModels TextAnalysis PyCall Chain Pipe Compose Gadfly Query Statistics StatsBase StableRNGs PrettyPrinting

lucifermorningstar1305

import numpy as np
from sklearn import preprocessing
features = np.array([[-500, 5], 
                    [2, 10],
                    [4, 100],
                    [9, 10]])
# Create the Standard Scaler
standard_scaler = preprocessing.StandardScaler()
# Apply the Standard Rescaling on our feature maps 
scaled_feature = standard_scaler.fit_transform(features)

lucifermorningstar1305

import numpy as np
from sklearn import preprocessing
features = np.array([[-500, 5], 
                    [2, 10],
                    [4, 100],
                    [9, 10]])
# Create the MinMax Scaler
minmax_scaler = preprocessing.MinMaxScaler(feature_range=(0,1))
# Apply the MinMax Rescaling on our feature maps 
scaled_feature = minmax_scaler.fit_transform(features)

lucifermorningstar1305