def run_test(df,
TRAIN_SIZE=6225,
TEST_SIZE=500,
BINARIO=False,
NEGACIONES=False,
NORMA_PESADA=False,
IDF=False,
STOP_WORDS=False):
print("--------------------------------------------------------")
print("Test empezado con:")
print("Train size:", TRAIN_SIZE)
print("Test size:", TEST_SIZE)
print("Negaciones:", NEGACIONES)
print("Binario:", BINARIO)
print("Norma pesada:", NORMA_PESADA)
print("Stop words:", STOP_WORDS)
print("IDF:", IDF)
text_train, label_train, text_test, label_test = get_instances(
df, TRAIN_SIZE, TEST_SIZE)
X_train, y_train, X_test, y_test = vectorizar(text_train, label_train,
text_test, label_test,
BINARIO, IDF, NEGACIONES,
STOP_WORDS)
X_train = X_train.todense()
var_total = np.std(X_train, axis=1).sum()
pca = PCA(1500)
pca.fit(X_train)
X_train = pca.transform(X_train, 1500)
X_train = tomar_porcentaje(X_train, 0.03, var_total) #MODIFICAR
X_test = pca.transform(X_test, X_train.shape[1])
print("ALPHA =", X_train.shape[1])
clf = KNNClassifier(1)
clf.fit(X_train, y_train)
mat = []
if not NORMA_PESADA:
mat = clf.testearK(X_test)
else:
y_train_norm = y_train - y_train.mean()
ystd = np.std(y_train)
covarianzas = np.zeros(X_train.shape[1])
correlaciones = np.zeros(X_train.shape[1])
for i in range(X_train.shape[1]):
covarianzas[i] = ((X_train[:, i] - X_train[:, i].mean()) *
y_train_norm).sum()
correlaciones[i] = covarianzas[i] / (np.std(X_train[:, i]) * ystd)
mat = clf.testearK_weighted(X_test, covarianzas)
vAcc = []
for i in range(len(mat[0])):
a = mat[:, i]
acc = accuracy_score(y_test, a)
vAcc.append(acc)
return vAcc
def main(args):
# datasets de train y test
df = pd.read_csv("data/imdb_small.csv")
#recortando data set para pruebas chiquitas
if (args.elem > 0):
df = df[:args.elem]
X_train, y_train, X_test, y_test = get_instances(df)
alpha = args.alpha_Start
# rango de k
k_range = np.arange(args.k_Start, args.k_Stop, args.k_Step)
# rango de alpha
alpha_range = np.arange(alpha, args.alpha_Stop, args.alpha_Step)
# resultados de accuaracies para cada k
results = []
for i in range(len(k_range)):
results.append([])
for alpha in alpha_range:
pca = PCA(alpha)
pca.fit(X_train.toarray())
X_train_aux = pca.transform(X_train)
X_test_aux = pca.transform(X_test)
# kNN
for i in range(len(k_range)):
k = k_range[i]
clf = KNNClassifier(k)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
t = accuracy_score(y_test, y_pred)
results[i].append(t)
for i, result in enumerate(results):
plt.plot(alpha_range, result, label='k = {0}'.format(k_range[i]))
plt.xlabel('alpha')
plt.ylabel('accuaracy')
plt.legend()
plt.savefig('results/k_vs_accuaracy-{}'.format(
time.strftime("%Y%m%d-%H%M%S")))
plt.show()
'''
def evaluate_knn(k_range, X_train, y_train, X_test, y_test, reps):
accs = []
# kNN
for k in k_range:
t = 0
for i in range(reps):
clf = KNNClassifier(k)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
t += accuracy_score(y_test, y_pred)
accs.append(t / reps)
return accs
def main(args):
# datasets de train y test
df = pd.read_csv("data/imdb_small.csv")
x_poda_frec = np.arange(args._from, args.to, args.step)
y_poda_frec = []
df = df[:6000]
for i in x_poda_frec:
X_train, y_train, X_test, y_test = get_instances(df, 0.9, i)
k = 500
alpha = 50
#pca
pca = PCA(alpha)
pca.fit(X_train.toarray())
X_train_aux = pca.transform(X_train)
X_test_aux = pca.transform(X_test)
#knn
clf = KNNClassifier(k)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
acc = accuracy_score(y_test, y_pred)
y_poda_frec.append(acc)
fig, ax1 = plt.subplots()
plt.plot(x_poda_frec, y_poda_frec, label='k = 500, alpha = 50'.format(k))
plt.xlabel('min_df')
plt.ylabel('accuaracy')
plt.legend()
plt.savefig('results/min_df_accuaracy-{}'.format(
time.strftime("%Y%m%d-%H%M%S")))
plt.show()
print("Uso: python classify archivo_de_test archivo_salida")
exit()
test_path = sys.argv[1]
out_path = sys.argv[2]
df = pd.read_csv("data/imdb_small.csv")
df_test = pd.read_csv(test_path)
print("Vectorizando datos...")
X_train, y_train, X_test, ids_test = get_instances(df, df_test)
"""
Entrenamos KNN
"""
clf = KNNClassifier(1120)
clf.fit(X_train, y_train)
"""
Testeamos
"""
print("Prediciendo etiquetas...")
y_pred = clf.predict(X_test).reshape(-1)
labels = ['pos' if val == 1 else 'neg' for val in y_pred]
df_out = pd.DataFrame({"id": ids_test, "label": labels})
df_out.to_csv(out_path, index=False)
print("Salida guardada en {}".format(out_path))
def run_test(df,
TRAIN_SIZE=6225,
TEST_SIZE=500,
ALPHA=None,
K=None,
BINARIO=False,
NEGACIONES=False,
NORMA_PESADA=False,
IDF=False,
STOP_WORDS=False):
print("--------------------------------------------------------")
print("Test empezado con:")
print("Train size:", TRAIN_SIZE)
print("Test size:", TEST_SIZE)
print("Alpha:", ALPHA)
print("K:", K)
print("Negaciones:", NEGACIONES)
print("Binario:", BINARIO)
print("Norma pesada:", NORMA_PESADA)
print("Stop words:", STOP_WORDS)
print("IDF:", IDF)
text_train, label_train, text_test, label_test = get_instances(
df, TRAIN_SIZE, TEST_SIZE)
print("Vectorizando...")
X_train, y_train, X_test, y_test = vectorizar(text_train, label_train,
text_test, label_test,
BINARIO, IDF, NEGACIONES,
STOP_WORDS)
if ALPHA != None:
print("Obteniendo componentes principales...")
pca = PCA(ALPHA)
pca.fit(X_train.todense())
X_train = pca.transform(X_train, ALPHA)
X_test = pca.transform(X_test, ALPHA)
clf = KNNClassifier(K)
clf.fit(X_train, y_train)
print("Prediciendo...")
if not NORMA_PESADA:
y_pred = clf.predict(X_test)
else:
y_train_norm = y_train - y_train.mean()
ystd = np.std(y_train)
covarianzas = np.zeros(X_train.shape[1])
correlaciones = np.zeros(X_train.shape[1])
for i in range(X_train.shape[1]):
if ALPHA:
covarianzas[i] = ((X_train[:, i] - X_train[:, i].mean()) *
y_train_norm).sum()
correlaciones[i] = covarianzas[i] / (np.std(X_train[:, i]) *
ystd)
else:
covarianzas[i] = ((
(X_train.todense())[:, i] - X_train[:, i].mean()) *
y_train_norm).sum()
correlaciones[i] = covarianzas[i] / (np.std(
(X_train.todense())[:, i]) * ystd)
y_pred = clf.predict_weighted(X_test, np.abs(correlaciones))
print("Test finalizado")
acc = accuracy_score(y_test, y_pred)
print("Accuracy: {}".format(acc))
return acc
df = pd.read_csv("../data/imdb_small.csv")
df['label'] = (df['label'] == 'pos').astype('int')
TOTAL_TRAIN = 6000
text_train, label_train, text_test, label_test = get_instances(df,TOTAL_TRAIN,TEST_SIZE)
print("Vectorizando...")
X_train, y_train, X_test, y_test = vectorizar(text_train, label_train, text_test, label_test, BINARIO, IDF, NEGACIONES, STOP_WORDS)
TRAIN = 1000
saltoTRAIN = 1000
mAcc = []
while TRAIN <= 6000:
print(TRAIN)
clf = KNNClassifier(1)
clf.fit(X_train[:TRAIN], y_train[:TRAIN])
mat = []
mat = clf.testearK(X_test)
vAcc = []
for i in range(len(mat[0])):
a = mat[:, i]
acc = accuracy_score(y_test, a)
vAcc.append(acc)
mAcc.append(vAcc)
TRAIN += saltoTRAIN
fout = open("resultados_exp5.pkl","wb")
pickle.dump(mAcc,fout)
fout.close()