##### Beginning of file

# This file was generated by PredictMD version 0.19.0
# For help, please visit https://www.predictmd.net

import PredictMD

### Begin project-specific settings

PredictMD.require_julia_version("v0.6")

PredictMD.require_predictmd_version("0.19.0")

# PredictMD.require_predictmd_version("0.19.0", "0.20.0-")

PROJECT_OUTPUT_DIRECTORY = PredictMD.project_directory(
    homedir(),
    "Desktop",
    "boston_housing_example",
    )

### End project-specific settings

### Begin data preprocessing code

import CSV
import Compat
import DataFrames
import FileIO
import GZip
import JLD2
import StatsBase

srand(999)

df = CSV.read(
    GZip.gzopen(
        joinpath(
            Pkg.dir("RDatasets"),
            "data",
            "MASS",
            "Boston.csv.gz",
            ),
        ),
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )

categorical_feature_names = Symbol[]
continuous_feature_names = Symbol[
    :Crim,
    :Zn,
    :Indus,
    :Chas,
    :NOx,
    :Rm,
    :Age,
    :Dis,
    :Rad,
    :Tax,
    :PTRatio,
    :Black,
    :LStat,
    ]
categorical_feature_names_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "categorical_feature_names.jld2",
    )
continuous_feature_names_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "continuous_feature_names.jld2",
    )
FileIO.save(
    categorical_feature_names_filename,
    "categorical_feature_names",
    categorical_feature_names,
    )
FileIO.save(
    continuous_feature_names_filename,
    "continuous_feature_names",
    continuous_feature_names,
    )
feature_names = vcat(categorical_feature_names, continuous_feature_names)

single_label_name = :MedV

continuous_label_names = Symbol[single_label_name]
categorical_label_names = Symbol[]
label_names = vcat(categorical_label_names, continuous_label_names)

df = df[:, vcat(feature_names, label_names)]
DataFrames.dropmissing!(df)
PredictMD.shuffle_rows!(df)

PredictMD.fix_column_types!(
    df;
    categorical_feature_names = categorical_feature_names,
    continuous_feature_names = continuous_feature_names,
    categorical_label_names = categorical_label_names,
    continuous_label_names = continuous_label_names,
    )
PredictMD.check_column_types(
    df;
    categorical_feature_names = categorical_feature_names,
    continuous_feature_names = continuous_feature_names,
    categorical_label_names = categorical_label_names,
    continuous_label_names = continuous_label_names,
    )
PredictMD.check_no_constant_columns(df)

features_df = df[feature_names]
labels_df = df[label_names]

DataFrames.describe(labels_df[single_label_name])

(trainingandvalidation_features_df,
    trainingandvalidation_labels_df,
    testing_features_df,
    testing_labels_df,) = PredictMD.split_data(
        features_df,
        labels_df,
        0.75,
        )
(training_features_df,
    training_labels_df,
    validation_features_df,
    validation_labels_df,) = PredictMD.split_data(
        trainingandvalidation_features_df,
        trainingandvalidation_labels_df,
        2/3,
        )

trainingandvalidation_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "trainingandvalidation_features_df.csv",
    )
trainingandvalidation_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "trainingandvalidation_labels_df.csv",
    )
testing_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "testing_features_df.csv",
    )
testing_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "testing_labels_df.csv",
    )
training_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "training_features_df.csv",
    )
training_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "training_labels_df.csv",
    )
validation_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "validation_features_df.csv",
    )
validation_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "validation_labels_df.csv",
    )
CSV.write(
    trainingandvalidation_features_df_filename,
    trainingandvalidation_features_df,
    )
CSV.write(
    trainingandvalidation_labels_df_filename,
    trainingandvalidation_labels_df,
    )
CSV.write(
    testing_features_df_filename,
    testing_features_df,
    )
CSV.write(
    testing_labels_df_filename,
    testing_labels_df,
    )
CSV.write(
    training_features_df_filename,
    training_features_df,
    )
CSV.write(
    training_labels_df_filename,
    training_labels_df,
    )
CSV.write(
    validation_features_df_filename,
    validation_features_df,
    )
CSV.write(
    validation_labels_df_filename,
    validation_labels_df,
    )

### End data preprocessing code

##### End of file

Summary Stats:
Mean:           22.532799
Minimum:        5.000000
1st Quartile:   17.025000
Median:         21.200001
3rd Quartile:   25.000000
Maximum:        50.000000
Length:         506
Type:           Float32

This page was generated using Literate.jl.