new changes

.gitignore

@@ -0,0 +1,10 @@
+### Example user template template
+### Example user template
+
+# IntelliJ project files
+.idea
+*.iml
+out
+gen
+.DS_store
+CICD-for-Machine-Learning

Makefile

@@ -0,0 +1,17 @@
+install:
+	pip install --upgrade pip && pip install -r requirements.txt
+
+format:
+	black *.py
+
+train:
+	python train.python
+
+eval:
+	echo 'Model metrics' > report.md
+	cat ./results/metrics.txt >> report.md
+
+	echo '\n Confusion Matrix Plot' >> report.md
+	echo '![Confusion Matrix](./results/model_results.png)' >> report.md
+
+	cml comment create report.md

data/drug200.csv

@@ -0,0 +1,201 @@
+Age,Sex,BP,Cholesterol,Na_to_K,Drug
+23,F,HIGH,HIGH,25.355,DrugY
+47,M,LOW,HIGH,13.093,drugC
+47,M,LOW,HIGH,10.114,drugC
+28,F,NORMAL,HIGH,7.798,drugX
+61,F,LOW,HIGH,18.043,DrugY
+22,F,NORMAL,HIGH,8.607,drugX
+49,F,NORMAL,HIGH,16.275,DrugY
+41,M,LOW,HIGH,11.037,drugC
+60,M,NORMAL,HIGH,15.171,DrugY
+43,M,LOW,NORMAL,19.368,DrugY
+47,F,LOW,HIGH,11.767,drugC
+34,F,HIGH,NORMAL,19.199,DrugY
+43,M,LOW,HIGH,15.376,DrugY
+74,F,LOW,HIGH,20.942,DrugY
+50,F,NORMAL,HIGH,12.703,drugX
+16,F,HIGH,NORMAL,15.516,DrugY
+69,M,LOW,NORMAL,11.455,drugX
+43,M,HIGH,HIGH,13.972,drugA
+23,M,LOW,HIGH,7.298,drugC
+32,F,HIGH,NORMAL,25.974,DrugY
+57,M,LOW,NORMAL,19.128,DrugY
+63,M,NORMAL,HIGH,25.917,DrugY
+47,M,LOW,NORMAL,30.568,DrugY
+48,F,LOW,HIGH,15.036,DrugY
+33,F,LOW,HIGH,33.486,DrugY
+28,F,HIGH,NORMAL,18.809,DrugY
+31,M,HIGH,HIGH,30.366,DrugY
+49,F,NORMAL,NORMAL,9.381,drugX
+39,F,LOW,NORMAL,22.697,DrugY
+45,M,LOW,HIGH,17.951,DrugY
+18,F,NORMAL,NORMAL,8.75,drugX
+74,M,HIGH,HIGH,9.567,drugB
+49,M,LOW,NORMAL,11.014,drugX
+65,F,HIGH,NORMAL,31.876,DrugY
+53,M,NORMAL,HIGH,14.133,drugX
+46,M,NORMAL,NORMAL,7.285,drugX
+32,M,HIGH,NORMAL,9.445,drugA
+39,M,LOW,NORMAL,13.938,drugX
+39,F,NORMAL,NORMAL,9.709,drugX
+15,M,NORMAL,HIGH,9.084,drugX
+73,F,NORMAL,HIGH,19.221,DrugY
+58,F,HIGH,NORMAL,14.239,drugB
+50,M,NORMAL,NORMAL,15.79,DrugY
+23,M,NORMAL,HIGH,12.26,drugX
+50,F,NORMAL,NORMAL,12.295,drugX
+66,F,NORMAL,NORMAL,8.107,drugX
+37,F,HIGH,HIGH,13.091,drugA
+68,M,LOW,HIGH,10.291,drugC
+23,M,NORMAL,HIGH,31.686,DrugY
+28,F,LOW,HIGH,19.796,DrugY
+58,F,HIGH,HIGH,19.416,DrugY
+67,M,NORMAL,NORMAL,10.898,drugX
+62,M,LOW,NORMAL,27.183,DrugY
+24,F,HIGH,NORMAL,18.457,DrugY
+68,F,HIGH,NORMAL,10.189,drugB
+26,F,LOW,HIGH,14.16,drugC
+65,M,HIGH,NORMAL,11.34,drugB
+40,M,HIGH,HIGH,27.826,DrugY
+60,M,NORMAL,NORMAL,10.091,drugX
+34,M,HIGH,HIGH,18.703,DrugY
+38,F,LOW,NORMAL,29.875,DrugY
+24,M,HIGH,NORMAL,9.475,drugA
+67,M,LOW,NORMAL,20.693,DrugY
+45,M,LOW,NORMAL,8.37,drugX
+60,F,HIGH,HIGH,13.303,drugB
+68,F,NORMAL,NORMAL,27.05,DrugY
+29,M,HIGH,HIGH,12.856,drugA
+17,M,NORMAL,NORMAL,10.832,drugX
+54,M,NORMAL,HIGH,24.658,DrugY
+18,F,HIGH,NORMAL,24.276,DrugY
+70,M,HIGH,HIGH,13.967,drugB
+28,F,NORMAL,HIGH,19.675,DrugY
+24,F,NORMAL,HIGH,10.605,drugX
+41,F,NORMAL,NORMAL,22.905,DrugY
+31,M,HIGH,NORMAL,17.069,DrugY
+26,M,LOW,NORMAL,20.909,DrugY
+36,F,HIGH,HIGH,11.198,drugA
+26,F,HIGH,NORMAL,19.161,DrugY
+19,F,HIGH,HIGH,13.313,drugA
+32,F,LOW,NORMAL,10.84,drugX
+60,M,HIGH,HIGH,13.934,drugB
+64,M,NORMAL,HIGH,7.761,drugX
+32,F,LOW,HIGH,9.712,drugC
+38,F,HIGH,NORMAL,11.326,drugA
+47,F,LOW,HIGH,10.067,drugC
+59,M,HIGH,HIGH,13.935,drugB
+51,F,NORMAL,HIGH,13.597,drugX
+69,M,LOW,HIGH,15.478,DrugY
+37,F,HIGH,NORMAL,23.091,DrugY
+50,F,NORMAL,NORMAL,17.211,DrugY
+62,M,NORMAL,HIGH,16.594,DrugY
+41,M,HIGH,NORMAL,15.156,DrugY
+29,F,HIGH,HIGH,29.45,DrugY
+42,F,LOW,NORMAL,29.271,DrugY
+56,M,LOW,HIGH,15.015,DrugY
+36,M,LOW,NORMAL,11.424,drugX
+58,F,LOW,HIGH,38.247,DrugY
+56,F,HIGH,HIGH,25.395,DrugY
+20,M,HIGH,NORMAL,35.639,DrugY
+15,F,HIGH,NORMAL,16.725,DrugY
+31,M,HIGH,NORMAL,11.871,drugA
+45,F,HIGH,HIGH,12.854,drugA
+28,F,LOW,HIGH,13.127,drugC
+56,M,NORMAL,HIGH,8.966,drugX
+22,M,HIGH,NORMAL,28.294,DrugY
+37,M,LOW,NORMAL,8.968,drugX
+22,M,NORMAL,HIGH,11.953,drugX
+42,M,LOW,HIGH,20.013,DrugY
+72,M,HIGH,NORMAL,9.677,drugB
+23,M,NORMAL,HIGH,16.85,DrugY
+50,M,HIGH,HIGH,7.49,drugA
+47,F,NORMAL,NORMAL,6.683,drugX
+35,M,LOW,NORMAL,9.17,drugX
+65,F,LOW,NORMAL,13.769,drugX
+20,F,NORMAL,NORMAL,9.281,drugX
+51,M,HIGH,HIGH,18.295,DrugY
+67,M,NORMAL,NORMAL,9.514,drugX
+40,F,NORMAL,HIGH,10.103,drugX
+32,F,HIGH,NORMAL,10.292,drugA
+61,F,HIGH,HIGH,25.475,DrugY
+28,M,NORMAL,HIGH,27.064,DrugY
+15,M,HIGH,NORMAL,17.206,DrugY
+34,M,NORMAL,HIGH,22.456,DrugY
+36,F,NORMAL,HIGH,16.753,DrugY
+53,F,HIGH,NORMAL,12.495,drugB
+19,F,HIGH,NORMAL,25.969,DrugY
+66,M,HIGH,HIGH,16.347,DrugY
+35,M,NORMAL,NORMAL,7.845,drugX
+47,M,LOW,NORMAL,33.542,DrugY
+32,F,NORMAL,HIGH,7.477,drugX
+70,F,NORMAL,HIGH,20.489,DrugY
+52,M,LOW,NORMAL,32.922,DrugY
+49,M,LOW,NORMAL,13.598,drugX
+24,M,NORMAL,HIGH,25.786,DrugY
+42,F,HIGH,HIGH,21.036,DrugY
+74,M,LOW,NORMAL,11.939,drugX
+55,F,HIGH,HIGH,10.977,drugB
+35,F,HIGH,HIGH,12.894,drugA
+51,M,HIGH,NORMAL,11.343,drugB
+69,F,NORMAL,HIGH,10.065,drugX
+49,M,HIGH,NORMAL,6.269,drugA
+64,F,LOW,NORMAL,25.741,DrugY
+60,M,HIGH,NORMAL,8.621,drugB
+74,M,HIGH,NORMAL,15.436,DrugY
+39,M,HIGH,HIGH,9.664,drugA
+61,M,NORMAL,HIGH,9.443,drugX
+37,F,LOW,NORMAL,12.006,drugX
+26,F,HIGH,NORMAL,12.307,drugA
+61,F,LOW,NORMAL,7.34,drugX
+22,M,LOW,HIGH,8.151,drugC
+49,M,HIGH,NORMAL,8.7,drugA
+68,M,HIGH,HIGH,11.009,drugB
+55,M,NORMAL,NORMAL,7.261,drugX
+72,F,LOW,NORMAL,14.642,drugX
+37,M,LOW,NORMAL,16.724,DrugY
+49,M,LOW,HIGH,10.537,drugC
+31,M,HIGH,NORMAL,11.227,drugA
+53,M,LOW,HIGH,22.963,DrugY
+59,F,LOW,HIGH,10.444,drugC
+34,F,LOW,NORMAL,12.923,drugX
+30,F,NORMAL,HIGH,10.443,drugX
+57,F,HIGH,NORMAL,9.945,drugB
+43,M,NORMAL,NORMAL,12.859,drugX
+21,F,HIGH,NORMAL,28.632,DrugY
+16,M,HIGH,NORMAL,19.007,DrugY
+38,M,LOW,HIGH,18.295,DrugY
+58,F,LOW,HIGH,26.645,DrugY
+57,F,NORMAL,HIGH,14.216,drugX
+51,F,LOW,NORMAL,23.003,DrugY
+20,F,HIGH,HIGH,11.262,drugA
+28,F,NORMAL,HIGH,12.879,drugX
+45,M,LOW,NORMAL,10.017,drugX
+39,F,NORMAL,NORMAL,17.225,DrugY
+41,F,LOW,NORMAL,18.739,DrugY
+42,M,HIGH,NORMAL,12.766,drugA
+73,F,HIGH,HIGH,18.348,DrugY
+48,M,HIGH,NORMAL,10.446,drugA
+25,M,NORMAL,HIGH,19.011,DrugY
+39,M,NORMAL,HIGH,15.969,DrugY
+67,F,NORMAL,HIGH,15.891,DrugY
+22,F,HIGH,NORMAL,22.818,DrugY
+59,F,NORMAL,HIGH,13.884,drugX
+20,F,LOW,NORMAL,11.686,drugX
+36,F,HIGH,NORMAL,15.49,DrugY
+18,F,HIGH,HIGH,37.188,DrugY
+57,F,NORMAL,NORMAL,25.893,DrugY
+70,M,HIGH,HIGH,9.849,drugB
+47,M,HIGH,HIGH,10.403,drugA
+65,M,HIGH,NORMAL,34.997,DrugY
+64,M,HIGH,NORMAL,20.932,DrugY
+58,M,HIGH,HIGH,18.991,DrugY
+23,M,HIGH,HIGH,8.011,drugA
+72,M,LOW,HIGH,16.31,DrugY
+72,M,LOW,HIGH,6.769,drugC
+46,F,HIGH,HIGH,34.686,DrugY
+56,F,LOW,HIGH,11.567,drugC
+16,M,LOW,HIGH,12.006,drugC
+52,M,NORMAL,HIGH,9.894,drugX
+23,M,NORMAL,NORMAL,14.02,drugX
+40,F,LOW,NORMAL,11.349,drugX

results/metrics.txt

@@ -0,0 +1,2 @@
+
+Accuracy=0.98, F1_score = 0.94

train.py

@@ -0,0 +1,66 @@
+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 data.
+drug_df = pd.read_csv("./data/drug200.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)),
+    ]
+)
+
+# train
+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
+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_result.png", dpi=120)
+
+# Write metrics to files
+with open("./results/metrics.txt", "w") as outfile:
+    outfile.write(f"\nAccuracy={round(accuracy, 2)}, F1_score = {round(f1, 2)}")
+
+# Save the model
+sio.dump(pipe, "./model/drug_pipeline.skops")