scrap.qmd

---
title: "Untitled"
format: html
editor: visual
---

## Quarto

Quarto enables you to weave together content and executable code into a finished document. To learn more about Quarto see <https://quarto.org>.

## Running Code

When you click the **Render** button a document will be generated that includes both content and the output of embedded code. You can embed code like this:

```{python}
import pandas as pd
import seaborn as sns
import numpy as np
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from formulaic import model_matrix
import statsmodels.api as sm

nhanes = pd.read_csv("classroom_data/NHANES.csv")
nhanes['Hypertension'] = (nhanes['BPDiaAve'] > 80) | (nhanes['BPSysAve'] > 130)

plt.clf()
sns.boxplot(x="Hypertension", y="BMI", data=nhanes)
plt.show()
```

```{python}
y, X = model_matrix("Hypertension ~ BMI", nhanes)

logit_model = sm.Logit(y, X).fit() 
```

```{python}
logit_model.summary()

plt.clf()
plt.scatter(X.BMI, logit_model.predict(), color="blue", label="Fitted Line")
plt.scatter(X.BMI, y, alpha=.3, color="brown", label="Data")
plt.axhline(y=0.5, color='r', linestyle='--', label='Prediction Cutoff')
plt.legend();
plt.show()

```

```{python}

from sklearn.metrics import (confusion_matrix, accuracy_score)

prediction_cut = [round(x) for x in logit_model.predict()]
cm = confusion_matrix(y, prediction_cut) 

print ("Confusion Matrix : \n", cm) 
print('Accuracy = ', accuracy_score(y, prediction_cut)) 
```

Different cutoff

```{python}
prediction_cut = [1 if x > .1 else 0 for x in logit_model.predict()]
cm = confusion_matrix(y, prediction_cut) 

print ("Confusion Matrix : \n", cm) 
tn, fp, fn, tp = confusion_matrix(y, prediction_cut).ravel().tolist()
print('Accuracy = ', accuracy_score(y, prediction_cut)) 
```

```{python}
from sklearn.metrics import roc_curve, roc_auc_score, RocCurveDisplay

y, X = model_matrix("Hypertension ~ BMI + Age", nhanes)
logit_model = sm.Logit(y, X).fit() 

logit_model.summary()

prediction_cut = [round(x) for x in logit_model.predict()]
cm = confusion_matrix(y, prediction_cut) 

print ("Confusion Matrix : \n", cm) 
print('Accuracy = ', accuracy_score(y, prediction_cut)) 

fpr, tpr, thresholds = roc_curve(y, logit_model.predict())

auc_score = roc_auc_score(y, logit_model.predict())

plt.figure(figsize=(8, 6))
RocCurveDisplay(fpr=fpr, tpr=tpr, roc_auc=auc_score, estimator_name='Logistic Regression').plot(ax=plt.gca())
plt.title('ROC Curve for Logistic Regression')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.show()
```