def load_pca():
my_data = genfromtxt('./results/joint_angle_data.csv', delimiter=',')
# print("PCA input shape is: ")
# print(my_data)
# print(my_data.shape)
# remember to do a transpose on the input
pca_matrix = run_pca(my_data.T)
return pca_matrix
def main():
if len(sys.argv) <= 2:
print('not enough cmd args')
exit()
Y, Yt = pca.run_pca()
#print('got data')
Z, Zt = randomize_data(Y, Yt)
'''h = 5
F, S = train(Y, Yt, 10, h)
FZ, SZ = train(Z, Zt, 10, h)
pwrite(F, S, sys.argv[2]+'total_model_10_'+str(h))
pwrite(FZ, SZ, sys.argv[2]+'total_randomized_10_'+str(h))
F_basic, S_basic = train_basic(Y, Yt, 10, h)
FZ_basic, SZ_basic = train_basic(Z, Zt, 10, h)
pwrite(F_basic, S_basic, sys.argv[2]+'basic_model_10_'+str(h))
pwrite(FZ_basic, SZ_basic, sys.argv[2]+'basic_randomized_10_'+str(h))'''
x = range(0,10)
for h in x:
try:
a = pread(out_dir+'pickled/models/total_model/total_model_10_' + str(h))
#b = pread( out_dir+'pickled/models/total_randomized/total_randomized_10_' + str(h))
c = pread(out_dir+'pickled/models/basic_model/basic_model_10_'+str(h))
#d = pread( out_dir+'pickled/models/basic_randomized/basic_randomized_10_'+str(h))
except:
try:
F, S = train(Y, Yt, 10, h)
#FZ, SZ = train(Z, Zt, 10, h)
pwrite(F, S, out_dir+'pickled/models/total_model/total_model_10_' + str(h))
#pwrite(FZ, SZ, out_dir+'pickled/models/total_randomized/total_randomized_10_' + str(h))
F_basic, S_basic = train_basic(Y, Yt, 10, h)
#FZ_basic, SZ_basic = train_basic(Z, Zt, 10, h)
pwrite(F_basic, S_basic, out_dir+'pickled/models/basic_model/basic_model_10_'+str(h))
#pwrite(FZ_basic, SZ_basic, out_dir+'pickled/models/basic_randomized/basic_randomized_10_'+str(h))
except:
print('Singular matrix: ' + str(h))
train_random()
run_naive_bayes(x_train, x_test, y_train, y_test)
run_neural_network(x_train, x_test, y_train, y_test)
run_perceptron(x_train, x_test, y_train, y_test)
run_random_forest(x_train, x_test, y_train, y_test)
run_svm(x_train, x_test, y_train, y_test)
run_xg_boost(x_train, x_test, y_train, y_test)
print(
"\n-------------------------------------\nAccuracy with Voting in all 22 features:\n-------------------------------------"
)
run_voting(x_train, x_test, y_train, y_test)
print(
"\n-------------------------------------\nAccuracies with dimensionality reduction using PCA (5 components):\n-------------------------------------"
)
new_x_train, new_x_test = run_pca(x_train, x_test, y_train, y_test, 5)
run_decision_tree(new_x_train, new_x_test, y_train, y_test)
run_k_nearest_neighbour(new_x_train, new_x_test, y_train, y_test)
run_logistic_regression(new_x_train, new_x_test, y_train, y_test)
run_naive_bayes(new_x_train, new_x_test, y_train, y_test)
run_neural_network(new_x_train, new_x_test, y_train, y_test)
run_perceptron(new_x_train, new_x_test, y_train, y_test)
run_random_forest(new_x_train, new_x_test, y_train, y_test)
run_svm(new_x_train, new_x_test, y_train, y_test)
run_xg_boost(new_x_train, new_x_test, y_train, y_test)
print(
"\n-------------------------------------\nAccuracy with Voting along with PCA:\n-------------------------------------"
)
run_voting(new_x_train, new_x_test, y_train, y_test)
col.remove('type')
col = col[5:15]
sc = StandardScaler()
temp = sc.fit_transform(df_movie[col])
# df_movie[col] = temp
df_standard = df_movie[list(df_movie.describe().columns)]
return (df_movie, df_standard)
def classify(row):
if row['imdbRating'] >= 0 and row['imdbRating'] < 4:
return 0
elif row['imdbRating'] >= 4 and row['imdbRating'] < 7:
return 1
elif row['imdbRating'] >= 7 and row['imdbRating'] <= 10:
return 2
if __name__ == '__main__':
df_movie, df_standard = data_prepocessing()
run_pca(df_standard, df_movie)
df_knn = df_movie
df_knn["class"] = df_knn.apply(classify, axis=1)
run_knn(df_knn)
run_logistic_regression()
run_xgboost_cornell()
run_xgboost_imdb(df_knn)