rf = RandomForest(X_train, y_train)
rf.predict(X_test)
rf.set_prediction_data()
#rf.plot_num_deaths_per_age()
#rf.plot_num_deaths_per_gender()
#rf.ageScore(age)
#rf.genderScore(gender)
#rf.deathScore(death)
###############################
### KNN ###
knn = Knn(X_train, y_train)
knn.predict(X_test)
knn.set_prediction_data()
#knn.plot_num_patient_neg_summary_based_on_gender()
#knn.plot_num_patient_neg_summary_baseg_on_age()
#knn.plot_num_patient_neg_summary_based_on_is_from_wuhan()
#knn.ageScore(age)
#knn.genderScore(gender)
#knn.deathScore(death)
###################################
T_1 = df.drop(columns=[
'reporting date', 'summary', 'location', 'country', 'symptom', 'death'
])
T_1.replace(replace_map_comp_gender, inplace=True)
T_1.replace(replace_map_comp_age_descriptive, inplace=True)
.format(X_test.size, X_test.shape, X_test[0]))
print(
"Testing target (y_target) has {} elements\ny_test.shape = {} --> A single array of 30 elements\n"
.format(y_test.size, y_test.shape))
print("target_labels = {}".format(y_test))
### view data
# plt.figure()
# plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap, edgecolor='k', s=20)
# plt.show()
# a = [1, 1, 1, 2, 2, 3, 4, 5, 6]
# from collections import Counter
# most_common = Counter(a).most_common(1)
# print(most_common[0][0])
from KNN import Knn
clf = Knn(
k=5
) # instantiate a Knn classifier (clf) passing in the number of neighbors (default is 3)
clf.fit(X_train, y_train) # pass the training data to your Knn classifier
predictions = clf.predict(X_test)
# predict() algorithm...
# 1) calculate distance between X_test and every training data entry
# 2) find kth nearest training data entries i.e. smallest euclidean distance
# 3) match kth nearest data entries with flower class target array and select the most common
acc = np.sum(predictions == y_test) / len(y_test)
print("accuracy = {}".format(acc))