I trained a basic FFNN on a example breast cancer dataset. For the results the precision_recall_curve function gives datapoints for 416 different thresholds. My Data contains 569 unique prediction values, as far as I understand the Precision Recall Curve I could apply 568 different threshold values and check the resulting Precision and Recall.
But how do I do so? is there a way to set the number of thresholds to test with sklearn? Or at least an explanation of how sklearn selects those thresholds?
I mean 417 should be enough, even for bigger data sets, I am just curious how they got selected.
# necessary packages
from sklearn.datasets import load_breast_cancer
import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
# load data
sk_data = load_breast_cancer(return_X_y=False)
# safe data in pandas
data = sk_data['data']
target = sk_data['target']
target_names = sk_data['target_names']
feature_names = sk_data['feature_names']
data = pd.DataFrame(data=data, columns=feature_names)
# build ANN
model = Sequential()
model.add(Dense(64, kernel_initializer='random_uniform', input_dim=30, activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(32, kernel_initializer='random_uniform', activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(1, activation='sigmoid'))
# train ANN
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
model.fit(data, target, epochs=50, batch_size=10, validation_split=0.2)
# eval
pred = model.predict(data)
# calculate precision-recall curve
from sklearn.metrics import precision_recall_curve
precision, recall, thresholds = precision_recall_curve(target, pred)
# precision-recall curve and f1
import matplotlib.pyplot as plt
#pyplot.plot([0, 1], [0.5, 0.5], linestyle='--')
plt.plot(recall, precision, marker='.')
# show the plot
plt.show()
len(np.unique(pred)) #569
len(thresholds) # 417
