Introduction to Supervised Learning

class: center, middle

![:scale 40%](images/sklearn_logo.png)

### Intermediate Machine learning with scikit-learn

# Reminder: Scikit-learn API

Andreas C. Müller

Columbia University, scikit-learn

.smaller[https://github.com/amueller/ml-workshop-2-of-4]

---

class: center

# scikit-learn documentation
![:scale 60%](images/sklearn-docs.png)

<a href="http://scikit-learn.org/" style="color:black; font-size:50px; text-decoration:None" >scikit-learn.org</a>

---

# Other Resources

.center[
![:scale 25%](images/PDSH.png)   
![:scale 25%](images/imlp.png)   
![:scale 25%](images/esl.png)
]
Lecture: http://www.cs.columbia.edu/~amueller/comsw4995s19/schedule/

https://www.youtube.com/andreasmueller

Videos and more slides!

---
class: center

# Representing Data

![:scale 100%](images/matrix-representation.png)
---
class: center

# Training and Test Data

![:scale 80%](images/train-test-split.png)

---
class: center

# Supervised ML Workflow

![:scale 100%](images/supervised-ml-api.png)

---
# KNN with scikit-learn

```python
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y)

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train, y_train)
print("accuracy: ", knn.score(X_test, y_test)))
y_pred = knn.predict(X_test)
```
accuracy: 0.77

???

---
class: center, middle

# Sckit-Learn API Summary

![:scale 80%](images/api-table.png)

---
class: center, middle

# Notebook: Review of Supervised learning