Revisiting Machine Learning Datasets - Abalone

import time
import pickle
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.preprocessing import MaxAbsScaler
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error, mean_squared_log_error, median_absolute_error
import sklearn.metrics
from sklearn.linear_model import LinearRegression, BayesianRidge
from sklearn.tree import DecisionTreeRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import LinearSVR
from sklearn.ensemble import RandomForestRegressor
from skgarden.mondrian import MondrianForestRegressor
import xgboost

names = ["Sex", "Length", "Diameter", "Height", "Whole weight", "Shucked weight", "Viscera weight", "Shell weight", "Rings"]

inputData = pd.read_csv("./data/abalone.data", names=names)
display(inputData.sample(10))



sexEncoded = []
for i in range(len(inputData["Sex"].values)):
    if inputData["Sex"].values[i] == "M":
        value=1
    elif inputData["Sex"].values[i] == "F":
        value=0
    else:
        value=-1
    sexEncoded.append(value)
inputData["Sex"] = sexEncoded

display(inputData.describe())

y = inputData["Rings"]
X = inputData.copy(deep=True)
X.drop(["Rings"], axis=1, inplace=True)

scaler = MaxAbsScaler()
scaler.fit(X)
X = scaler.transform(X)
X = pd.DataFrame(X, columns=names[:-1])



# #Test set performance (final 1044 examples, first 3133 used for training)
X_train = X.values[0:3134]
X_test = X.values[3134:]
y_train = y[0:3134]
y_test = y[3134:]



datasets = {}
datasets[0] = {'X_train' : X_train,
               'X_test': X_test,
               'y_train':y_train,
               'y_test' : y_test}

import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import MaxAbsScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_log_error, mean_squared_error, mean_absolute_error
import sklearn.metrics
from tpot import TPOTRegressor



names = ["Sex", "Length", "Diameter", "Height", "Whole weight", "Shucked weight", "Viscera weight", "Shell weight", "Rings"]
inputData = pd.read_csv("./data/abalone.data", names=names)
sexEncoded = []
for i in range(len(inputData["Sex"].values)):
    if inputData["Sex"].values[i] == "M":
        value=1
    elif inputData["Sex"].values[i] == "F":
        value=0
    else:
        value=-1
    sexEncoded.append(value)
inputData["Sex"] = sexEncoded
y = inputData["Rings"]
X = inputData.copy(deep=True)
X.drop(["Rings"], axis=1, inplace=True)

scaler = MaxAbsScaler()
scaler.fit(X)
X = scaler.transform(X)
X = pd.DataFrame(X, columns=names[:-1])
X_train = X.values[0:3134]
X_test = X.values[3134:]
y_train = y[0:3134]
y_test = y[3134:]


tpot = TPOTRegressor(max_time_mins=60,
                     verbosity=1,
                     n_jobs=-1)
tpot.fit(X_train,y_train)
tpot.export('abalone.py')




y_predictions = tpot.predict(X_test)
r2 = sklearn.metrics.r2_score(y_test, y_predictions)
mae = sklearn.metrics.mean_absolute_error(y_test, y_predictions)
mse = sklearn.metrics.mean_squared_error(y_test.values, y_predictions)
rmse = np.sqrt(mse)
print("R2 score:", r2)
print("MAE:", mae)
print("MSE:", mse)
print("RMSE:", rmse)

import numpy as np
import pandas as pd
from sklearn.decomposition import FastICA
from sklearn.ensemble import ExtraTreesRegressor, RandomForestRegressor
from sklearn.feature_selection import SelectFromModel, SelectPercentile, f_regression
from sklearn.kernel_approximation import RBFSampler
from sklearn.linear_model import ElasticNetCV
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline, make_union
from tpot.builtins import StackingEstimator

# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
            train_test_split(features, tpot_data['target'].values, random_state=None)

# Average CV score on the training set was:-4.814505839419024
exported_pipeline = make_pipeline(
    SelectPercentile(score_func=f_regression, percentile=89),
    StackingEstimator(estimator=ElasticNetCV(l1_ratio=0.35000000000000003, tol=0.1)),
    SelectFromModel(estimator=ExtraTreesRegressor(max_features=0.6500000000000001, n_estimators=100), threshold=0.05),
    FastICA(tol=0.15000000000000002),
    RBFSampler(gamma=0.45),
    RandomForestRegressor(bootstrap=False, max_features=0.2, min_samples_leaf=20, min_samples_split=17, n_estimators=100)
)

exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)