def test_score_function():
lr = SoftmaxRegression(epochs=200,
eta=0.005,
minibatches=1,
random_seed=1)
lr.fit(X, y)
acc = lr.score(X, y)
assert acc == 1.0, acc
def test_score_function():
lr = SoftmaxRegression(epochs=200,
eta=0.005,
minibatches=1,
random_seed=1)
lr.fit(X, y)
acc = lr.score(X, y)
assert acc == 1.0, acc
def main():
#SETUP!!!
train = 0.9 #percetage of data for training
dev = 0.05 #percetage of data for development
test = 0.05 #percetage of data for test
n_features = 1500 #this could be adjusted later by the algorithm
#this is setting the CountVectorizer from sklearn.feature_extraction.text
vectorizer = CountVectorizer(
min_df=20, #you may want to adjust this
max_features=n_features,
lowercase=False)
DO_STANDARDIZE_DATA = 1 #1 yes, 0 no
regularization_lambda = 0.1
ETA = 0.00005
EPOCHS = 50
model_sm = SoftmaxRegression(
eta=ETA,
epochs=EPOCHS,
l2=regularization_lambda,
#n_classes=U,
minibatches=1,
random_seed=1,
print_progress=3)
print("-----------------------------")
print("METHOD - SOFTMAX REGRESSION")
print("-----------------------------")
print("Hello,\nwe will use Softmax Regression to classify twitter users\n")
setpath()
#get the users
screen_names = get_users(FILE_USERS)
info_data = get_info()
U = len(screen_names) #number of users
for i in range(U):
print("For", screen_names[i], " one has ", info_data[i, 1], "tweets")
if os.path.isfile(FOLDER + "/update_SM" + str(U) + ".txt") == True:
with open(FOLDER + "/update_SM" + str(U) + ".txt", "r") as h:
update = h.read()
h.close()
print("We load the dataset.")
file = FOLDER + "/X_train_politic" + update + ".npy"
with open(file, 'rb') as f:
X_train = pickle.load(f)
file = FOLDER + "/Y_train_politic" + update + ".npy"
with open(file, 'rb') as f:
Y_train = pickle.load(f)
file = FOLDER + "/X_dev_politic" + update + ".npy"
with open(file, 'rb') as f:
X_dev = pickle.load(f)
file = FOLDER + "/Y_dev_politic" + update + ".npy"
with open(file, 'rb') as f:
Y_dev = pickle.load(f)
file = FOLDER + "/X_test_politic" + update + ".npy"
with open(file, 'rb') as f:
X_test = pickle.load(f)
file = FOLDER + "/Y_test_politic" + update + ".npy"
with open(file, 'rb') as f:
Y_test = pickle.load(f)
else:
all_tweets = load_data()
random.shuffle(all_tweets)
random.shuffle(
all_tweets) #Always shuffle your opponent cards when you play :)
tweets = []
YY = []
for i in range(len(all_tweets)):
tweets.append(all_tweets[i][2])
YY.append(all_tweets[i][0])
if len(tweets) == len(all_tweets):
print("We load the data and we create the data set!")
Y = np.array(YY) #this is the output label vector
print("-----------------------------")
m = len(tweets)
X_train_1, x_appoggio, Y_train, y_appoggio = train_test_split(
tweets, Y, test_size=(dev + test))
X_dev_1, X_test_1, Y_dev, Y_test = train_test_split(
x_appoggio, y_appoggio, test_size=(test / (dev + test)))
print("We will train with the", train * 100, " % of the data;")
print(dev * 100,
"% of the data is reserve for the method development;")
print(test * 100, "% of the data is for the test.")
vectorizer.fit(X_train_1)
X_train = vectorizer.transform(X_train_1)
X_dev = vectorizer.transform(X_dev_1)
X_test = vectorizer.transform(X_test_1)
if DO_STANDARDIZE_DATA == 0:
print("We don't standardize data")
else:
print(
"We will provide to the model with standardize data, mean zero and variance 1"
)
X_train, X_dev, X_test = standardize_data(X_train, X_dev, X_test)
del (all_tweets)
del (X_train_1, X_dev_1, X_test_1, x_appoggio, y_appoggio)
today = date.today()
today_string = today.strftime("%y_%b_%d")
#we save the data we have prepared
with open(
FOLDER + "/X_train_politic" + today_string + "_SM" + str(U) +
".npy", 'wb') as f:
pickle.dump(X_train, f)
file = FOLDER + "/X_train_politic" + today_string + "_SM" + str(
U) + ".npy"
with open(file, "wb") as f:
pickle.dump(X_train, f)
file = FOLDER + "/Y_train_politic" + today_string + "_SM" + str(
U) + ".npy"
with open(file, "wb") as f:
pickle.dump(Y_train, f)
file = FOLDER + "/X_dev_politic" + today_string + "_SM" + str(
U) + ".npy"
with open(file, "wb") as f:
pickle.dump(X_dev, f)
file = FOLDER + "/Y_dev_politic" + today_string + "_SM" + str(
U) + ".npy"
with open(file, "wb") as f:
pickle.dump(Y_dev, f)
file = FOLDER + "/X_test_politic" + today_string + "_SM" + str(
U) + ".npy"
with open(file, "wb") as f:
pickle.dump(X_test, f)
file = FOLDER + "/Y_test_politic" + today_string + "_SM" + str(
U) + ".npy"
with open(file, "wb") as f:
pickle.dump(Y_test, f)
with open(FOLDER + "/update_SM" + str(U) + ".txt", "w") as h:
h.write(today_string + "_SM" + str(U))
h.close()
D = X_test.toarray().shape[1] #this is the lengh of the input vector
print("\n")
if n_features > D:
n_features = D
print("The # of features is", n_features)
print("The regularization parameter is", regularization_lambda)
print("The learning step is", ETA)
print("The # of cycle is", EPOCHS)
print("\n")
#WE START TRAINING THE MODEL
model_sm.fit(X_train.toarray(), Y_train)
acc = model_sm.score(X_train.toarray(), Y_train)
acc_dev = model_sm.score(X_dev.toarray(), Y_dev)
print("\n")
print("Accuracy on the training set", acc)
print("Accuracy on the development set", acc_dev)
#print some statistics about the model
df_score, df_fp, df_pre = compute_accuracies(model_sm, 1, screen_names,
X_train, X_dev, Y_train,
Y_dev)
y = data[:, data.shape[1] - 1] # Label - shape: 150, 1
X = data[:, 0:data.shape[1] - 1].astype(float) # Data - shape: 150, 4
X_train = X[0:105, :] #shape: 120, 4
X_test = X[105:X.shape[0], :] #30, 4
y_train = y[0:105] #shape: 120, 4
y_test = y[105:y.shape[0]] #30, 4
del data, X, y
# Map label sang 0, 1, 2
classes = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
y_train = [classes[item] for item in y_train]
y_test = [classes[item] for item in y_test]
y_train = np.asarray(y_train)
y_test = np.asarray(y_test)
# Softmax
softmax = SoftmaxRegression(eta=1 / (10 ^ 4),
epochs=500,
minibatches=1,
random_seed=0,
print_progress=3)
softmax.fit(X_train, y_train, init_params=True)
"""
plt.plot(range(len(softmax.cost_)), softmax.cost_)
plt.xlabel('Iterations')
plt.ylabel('Cost')
plt.show()
"""
accuracy = softmax.score(X_test, y_test)
print(accuracy)
