def select_baseline(df_pos_normalized: pd.DataFrame,
model: tf.keras.Sequential,
min_p: float = 0.85,
max_count: int = 100):
"""Selects the representative subsamnple that will be used as baselines.
Based on Proposition 3 (Baseline Set for Anomaly Detection) of
Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative
Sampling (Sipple 2020).
Args:
df_pos_normalized: data frame of the normalized positive sample.
model: classifier model from NS-NN.
min_p: minimum class score to be be considered as a baseline normal.
max_count: maximum number of reference points to be selected.
Returns:
data frame of the normalized baseline and the maximum conf score
"""
x = np.float32(np.matrix(df_pos_normalized))
y_hat = model.predict(x, verbose=1, steps=1)
df_pos_normalized[_CLASS_PROB_LABEL] = y_hat
high_scoring_predictions = df_pos_normalized[
df_pos_normalized[_CLASS_PROB_LABEL] >= min_p]
high_scoring_predictions = high_scoring_predictions.sort_values(
by=_CLASS_PROB_LABEL, ascending=False)
high_scoring_predictions = high_scoring_predictions.drop(
columns=[_CLASS_PROB_LABEL])
return high_scoring_predictions[:max_count], float(max(y_hat))
def __evaluate_model(self, model: tf.keras.Sequential, x_test: np.ndarray,
y_test: np.ndarray) -> None:
print('[INFO] evaluating network')
predictions = model.predict(x=x_test, batch_size=1024)
print(
classification_report(y_test,
predictions.round(),
target_names=['Male', 'Female']))
def discernHeadline(model: tf.keras.Sequential, tokenizer: Tokenizer):
# 预测一个实例
headline = [
"granny starting to fear spiders in the garden might be real",
"teh weather today is bright and sunny"
]
seq = tokenizer.texts_to_sequences(headline)
padded = pad_sequences(seq, maxlen=100, padding="post", truncating="post")
print(model.predict(padded))
def display_predictions(chosen_file: str, trained_model: tf.keras.Sequential,
original_columns_list):
"""
Fonction qui affiche les 10 premiers resultats comparant la prediction et la realite
:param chosen_file: chemin du fichier a comparer
:param trained_model: modele entraine pour afficher les predictions realisees
:param original_columns_list: nom des colonnes dans la DF avant nettoyage des donnees
:return: rien du tout
"""
df_test = pd.read_pickle(
chosen_file) # predictions sur le fichier d'origine pour comparer
df_test.columns = original_columns_list
df_test.set_index("MachineIdentifier", inplace=True)
df_test = cleaning_df(df_test)
predictions = trained_model.predict(df_test.iloc[:, :-1])
for i in range(0, 10):
print("predicted infection: {:.2%} | actual outcome : {}".format(
predictions[i][0], df_test.iloc[i, -1]))
def predict_monthly_payment(principal: float, interest_rate: float,
number_of_payments: float,
model: tf.keras.Sequential) -> float:
return model.predict([(principal, interest_rate, number_of_payments)
])[0][0]