fuzzy-rules-generator/temp_density_regression.ipynb

In [ ]:

import pandas as pd

train = pd.read_csv("data/density_train.csv", sep=";", decimal=",")
test = pd.read_csv("data/density_test.csv", sep=";", decimal=",")

display(train.head())
display(test.head())

	T	Al2O3	TiO2	Density
0	20	0.0	0.0	1.06250
1	25	0.0	0.0	1.05979
2	35	0.0	0.0	1.05404
3	40	0.0	0.0	1.05103
4	45	0.0	0.0	1.04794

	T	Al2O3	TiO2	Density
0	30	0.00	0.0	1.05696
1	55	0.00	0.0	1.04158
2	25	0.05	0.0	1.08438
3	30	0.05	0.0	1.08112
4	35	0.05	0.0	1.07781

In [3]:

y_train = train["T"]
X_train = train.drop(["T"], axis=1)

display(X_train.head())
display(y_train.head())

y_test = test["T"]
X_test = test.drop(["T"], axis=1)

display(X_test.head())
display(y_test.head())

	Al2O3	TiO2	Density
0	0.0	0.0	1.06250
1	0.0	0.0	1.05979
2	0.0	0.0	1.05404
3	0.0	0.0	1.05103
4	0.0	0.0	1.04794

0    20
1    25
2    35
3    40
4    45
Name: T, dtype: int64

	Al2O3	TiO2	Density
0	0.00	0.0	1.05696
1	0.00	0.0	1.04158
2	0.05	0.0	1.08438
3	0.05	0.0	1.08112
4	0.05	0.0	1.07781

0    30
1    55
2    25
3    30
4    35
Name: T, dtype: int64

In [29]:

from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn import linear_model, tree, neighbors, ensemble

random_state = 9

models = {
    "linear": {"model": linear_model.LinearRegression(n_jobs=-1)},
    "linear_poly": {
        "model": make_pipeline(
            PolynomialFeatures(degree=2),
            linear_model.LinearRegression(fit_intercept=False, n_jobs=-1),
        )
    },
    "linear_interact": {
        "model": make_pipeline(
            PolynomialFeatures(interaction_only=True),
            linear_model.LinearRegression(fit_intercept=False, n_jobs=-1),
        )
    },
    "ridge": {"model": linear_model.RidgeCV()},
    "decision_tree": {
        "model": tree.DecisionTreeRegressor(random_state=random_state, max_depth=6, criterion="absolute_error")
    },
    "knn": {"model": neighbors.KNeighborsRegressor(n_neighbors=7, n_jobs=-1)},
    "random_forest": {
        "model": ensemble.RandomForestRegressor(
            max_depth=7, random_state=random_state, n_jobs=-1
        )
    },
}

In [30]:

import math
from sklearn import metrics

for model_name in models.keys():
    print(f"Model: {model_name}")
    fitted_model = models[model_name]["model"].fit(
        X_train.values, y_train.values.ravel()
    )
    y_train_pred = fitted_model.predict(X_train.values)
    y_test_pred = fitted_model.predict(X_test.values)
    models[model_name]["fitted"] = fitted_model
    models[model_name]["MSE_train"] = metrics.mean_squared_error(y_train, y_train_pred)
    models[model_name]["MSE_test"] = metrics.mean_squared_error(y_test, y_test_pred)
    models[model_name]["MAE_train"] = metrics.mean_absolute_error(y_train, y_train_pred)
    models[model_name]["MAE_test"] = metrics.mean_absolute_error(y_test, y_test_pred)
    models[model_name]["R2_train"] = metrics.r2_score(y_train, y_train_pred)
    models[model_name]["R2_test"] = metrics.r2_score(y_test, y_test_pred)

Model: linear
Model: linear_poly
Model: linear_interact
Model: ridge
Model: decision_tree
Model: knn
Model: random_forest

In [31]:

reg_metrics = pd.DataFrame.from_dict(models, "index")[
    ["MSE_train", "MSE_test", "MAE_train", "MAE_test", "R2_train", "R2_test"]
]
reg_metrics.sort_values(by="MAE_test").style.background_gradient(
    cmap="viridis", low=1, high=0.3, subset=["MSE_train", "MSE_test"]
).background_gradient(cmap="plasma", low=0.3, high=1, subset=["MAE_test", "R2_test"])

Out[31]:

	MSE_train	MSE_test	MAE_train	MAE_test	R2_train	R2_test
linear_poly	0.302768	0.203293	0.419467	0.392687	0.998860	0.999047
linear_interact	9.693323	10.875442	2.544944	2.718424	0.963492	0.949019
linear	10.468503	14.820315	2.657476	2.930229	0.960572	0.930526
decision_tree	10.526316	47.426471	1.842105	5.735294	0.960355	0.777676
random_forest	20.243876	54.501240	3.592953	6.598133	0.923755	0.744512
knn	174.100430	191.176471	10.808271	11.680672	0.344285	0.103812
ridge	243.364664	199.601477	13.472724	12.396799	0.083415	0.064317

In [32]:

model = models["decision_tree"]["fitted"]
rules = tree.export_text(
    model, feature_names=X_train.columns.values.tolist()
)
print(rules)

|--- Density <= 1.04
|   |--- Density <= 1.03
|   |   |--- value: [70.00]
|   |--- Density >  1.03
|   |   |--- Density <= 1.04
|   |   |   |--- value: [65.00]
|   |   |--- Density >  1.04
|   |   |   |--- value: [60.00]
|--- Density >  1.04
|   |--- Density <= 1.07
|   |   |--- TiO2 <= 0.03
|   |   |   |--- Al2O3 <= 0.03
|   |   |   |   |--- Density <= 1.05
|   |   |   |   |   |--- Density <= 1.05
|   |   |   |   |   |   |--- value: [50.00]
|   |   |   |   |   |--- Density >  1.05
|   |   |   |   |   |   |--- value: [42.50]
|   |   |   |   |--- Density >  1.05
|   |   |   |   |   |--- Density <= 1.06
|   |   |   |   |   |   |--- value: [35.00]
|   |   |   |   |   |--- Density >  1.06
|   |   |   |   |   |   |--- value: [22.50]
|   |   |   |--- Al2O3 >  0.03
|   |   |   |   |--- Density <= 1.06
|   |   |   |   |   |--- Density <= 1.05
|   |   |   |   |   |   |--- value: [70.00]
|   |   |   |   |   |--- Density >  1.05
|   |   |   |   |   |   |--- value: [65.00]
|   |   |   |   |--- Density >  1.06
|   |   |   |   |   |--- Density <= 1.07
|   |   |   |   |   |   |--- value: [55.00]
|   |   |   |   |   |--- Density >  1.07
|   |   |   |   |   |   |--- value: [50.00]
|   |   |--- TiO2 >  0.03
|   |   |   |--- Density <= 1.06
|   |   |   |   |--- value: [70.00]
|   |   |   |--- Density >  1.06
|   |   |   |   |--- Density <= 1.06
|   |   |   |   |   |--- value: [65.00]
|   |   |   |   |--- Density >  1.06
|   |   |   |   |   |--- value: [60.00]
|   |--- Density >  1.07
|   |   |--- Density <= 1.12
|   |   |   |--- Density <= 1.08
|   |   |   |   |--- Density <= 1.07
|   |   |   |   |   |--- value: [45.00]
|   |   |   |   |--- Density >  1.07
|   |   |   |   |   |--- Density <= 1.08
|   |   |   |   |   |   |--- value: [40.00]
|   |   |   |   |   |--- Density >  1.08
|   |   |   |   |   |   |--- value: [35.00]
|   |   |   |--- Density >  1.08
|   |   |   |   |--- Density <= 1.09
|   |   |   |   |   |--- value: [30.00]
|   |   |   |   |--- Density >  1.09
|   |   |   |   |   |--- Al2O3 <= 0.03
|   |   |   |   |   |   |--- value: [22.50]
|   |   |   |   |   |--- Al2O3 >  0.03
|   |   |   |   |   |   |--- value: [20.00]
|   |   |--- Density >  1.12
|   |   |   |--- Density <= 1.18
|   |   |   |   |--- Density <= 1.15
|   |   |   |   |   |--- value: [70.00]
|   |   |   |   |--- Density >  1.15
|   |   |   |   |   |--- Al2O3 <= 0.15
|   |   |   |   |   |   |--- value: [65.00]
|   |   |   |   |   |--- Al2O3 >  0.15
|   |   |   |   |   |   |--- value: [50.00]
|   |   |   |--- Density >  1.18
|   |   |   |   |--- Al2O3 <= 0.15
|   |   |   |   |   |--- Density <= 1.20
|   |   |   |   |   |   |--- value: [50.00]
|   |   |   |   |   |--- Density >  1.20
|   |   |   |   |   |   |--- value: [30.00]
|   |   |   |   |--- Al2O3 >  0.15
|   |   |   |   |   |--- Density <= 1.18
|   |   |   |   |   |   |--- value: [30.00]
|   |   |   |   |   |--- Density >  1.18
|   |   |   |   |   |   |--- value: [22.50]

In [33]:

import pickle

pickle.dump(model, open("data/temp_density_tree.model.sav", "wb"))