Spaces:
Configuration error
Configuration error
File size: 1,956 Bytes
fe69984 |
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 |
import pandas as pd
import skops.io as sio
from sklearn.compose import ColumnTransformer
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from sklearn.metrics import accuracy_score, f1_score
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OrdinalEncoder, StandardScaler
# Loading the Data
drug_df = pd.read_csv("Data/drug.csv")
drug_df = drug_df.sample(frac=1)
# Train Test Split
from sklearn.model_selection import train_test_split
X = drug_df.drop("Drug", axis=1).values
y = drug_df.Drug.values
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=125
)
# Pipeline
cat_col = [1, 2, 3]
num_col = [0, 4]
transform = ColumnTransformer(
[
("encoder", OrdinalEncoder(), cat_col),
("num_imputer", SimpleImputer(strategy="median"), num_col),
("num_scaler", StandardScaler(), num_col),
]
)
pipe = Pipeline(
steps=[
("preprocessing", transform),
("model", RandomForestClassifier(n_estimators=10, random_state=125)),
]
)
# Training
pipe.fit(X_train, y_train)
# Model Evaluation
predictions = pipe.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
f1 = f1_score(y_test, predictions, average="macro")
print("Accuracy:", str(round(accuracy, 2) * 100) + "%", "F1:", round(f1, 2))
# Confusion Matrix Plot
import matplotlib.pyplot as plt
from sklearn.metrics import ConfusionMatrixDisplay, confusion_matrix
predictions = pipe.predict(X_test)
cm = confusion_matrix(y_test, predictions, labels=pipe.classes_)
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=pipe.classes_)
disp.plot()
plt.savefig("./Results/model_results.png", dpi=120)
# Write metrics to file
with open("./Results/metrics.txt", "w") as outfile:
outfile.write(f"\nAccuracy = {round(accuracy, 2)}, F1 Score = {round(f1, 2)}")
# Saving the model file
sio.dump(pipe, "./Model/drug_pipeline.skops")
|