def main(group_id):
#topiclist_path = 'data-dynamic/TopicList-' + group_id + 'shuffled-.txt' # for douban dataset
topiclist_path = 'data-dynamic/' + group_id + '-post-list.txt' # for Tianya dataset
topic_list = load_id_list(topiclist_path)
print 'Number of total topics loaded: ', len(topic_list)
pop_level = [25, 50, float('inf')]
# prediction_date 的含义为：在帖子发布 prediction_date 时间后，开始预测
# target_date 的含义为：预测在 target_date 处的评论数量
# 以上两个参数可以调节
# 设置采样的间隔
gaptime = timedelta(hours=3)
prediction_date = timedelta(hours=10*3)
response_time = timedelta(hours=24)
target_date = prediction_date + response_time
# 计算每个topic在prediction_date前会有多少个interval
num_feature = int(prediction_date.total_seconds() / gaptime.total_seconds())
print 'Number of features: ', num_feature
alpha = 1.5
percentage_threshold = 0.7
print 'Generating training and test dataset...'
dataset, comment_count_dataset, Bao_dataset, category_count_list = prepare_dataset(group_id, \
topic_list, gaptime, pop_level, prediction_date, target_date, alpha, percentage_threshold)
# 保存那些经过筛选的topic id
#save_filtered_topics(group_id, dataset)
print 'Ploting factor propagation'
#factor_propagation_plot(dataset, num_feature)
#topic_propagation_plot(dataset, num_feature)
#return
# 调整所有帖子的顺序
# 在调试阶段，暂且不shuffle dataset，避免每次结果都不一样
#shuffle(dataset)
# 注意：每次使用的数据集是不同的
total = len(dataset)
train_cnt = total * 4 / 5
train_set = dataset[:train_cnt]
test_set = dataset[train_cnt:]
print 'Training: %d, Test: %d' % (train_cnt, total-train_cnt)
print 'Category 0: %d, Category 1: %d ' % (category_count_list[0] , category_count_list[1])
print 'Imbalance ratio: ', category_count_list[0] * 1.0 / category_count_list[1]
dataset, comment_count_dataset, Bao_dataset, category_count_list = down_sampling_dataset(dataset, \
comment_count_dataset, Bao_dataset, category_count_list)
print 'After down sampling...'
total = len(dataset)
train_cnt = total * 4 / 5
train_set = dataset[:train_cnt]
test_set = dataset[train_cnt:]
print 'Training: %d, Test: %d' % (train_cnt, total-train_cnt)
print 'Category 0: %d, Category 1: %d ' % (category_count_list[0] , category_count_list[1])
print 'Imbalance ratio: ', category_count_list[0] * 1.0 / category_count_list[1]
def select_k(group_id, topic_list, percentage_threshold, prediction_date, response_time, cvk):
# sampling interval
gaptime = timedelta(hours=5)
target_date = prediction_date + response_time
num_feature = int(prediction_date.total_seconds() / gaptime.total_seconds())
print "Number of features: ", num_feature
# percentage_threshold = 0.7
alpha = 1 / percentage_threshold
pop_level = [25, 50, float("inf")] # group: zhuangb
print "Generating training and test dataset..."
dataset, comment_count_dataset, Bao_dataset, category_count_list = prepare_dataset(
group_id, topic_list, gaptime, pop_level, prediction_date, target_date, alpha, percentage_threshold
)
print "Down-sampling the datasets..."
dataset, comment_count_dataset, Bao_dataset, category_count_list = down_sampling_dataset(
dataset, comment_count_dataset, Bao_dataset, category_count_list
)
total = len(dataset)
n_folds = 3
kf = KFold(total, n_folds)
IPW_acc_list = []
for cv_train_index, cv_test_index in kf:
train_set = make_cv_dataset(dataset, cv_train_index)
test_set = make_cv_dataset(dataset, cv_test_index)
train_cnt = len(train_set)
print "Training: %d, Test: %d" % (train_cnt, total - train_cnt)
print "Category 0: %d, Category 1: %d " % (category_count_list[0], category_count_list[1])
print "Imbalance ratio: ", category_count_list[0] * 1.0 / category_count_list[1]
num_level = 2
num_factor = len(train_set[0][1][1])
print "The proposed model:"
print "Caculating instance prior score..."
prior_score = -1
mutual_knn_graph_list = None
# prior_score = caculate_instance_prior_confidence_score(train_set, k, num_level = 2) # for instance_prior_weighting3.py
topic_popularity, prior_score, mutual_knn_graph_list = caculate_instance_prior_confidence_score(
train_set, test_set, cvk, num_factor, num_level=2
) # for IPW_mutual_knn.py
print "Classify test instances..."
y_true, y_pred, comment_true, comment_pred, give_up_list, prediction_list, factor_prediction = classify(
train_set, test_set, cvk, num_factor, num_level, prior_score, topic_popularity, mutual_knn_graph_list
)
# evaluate results
print "Number of give-ups: ", len(give_up_list)
IPW_acc = classification_evaluation(y_true, y_pred)
IPW_acc_list.append(IPW_acc)
return IPW_acc_list
def main(group_id):
topiclist_path = 'data-dynamic/TopicList-' + group_id + '-filtered.txt'
topic_list = load_id_list(topiclist_path)
print 'Number of total topics loaded: ', len(topic_list)
# set the pre-computed popularity level
# 未来的最大评论数可能超过pop_level的最大值
# 注意：这里将最小的popularity值，即0，忽略了
#pop_level = [8, 13, 23, 43, float('inf')] # group: zhuangb
pop_level = [25, 50, float('inf')] # group: zhuangb
#pop_level = [25, 50, float('inf')] # group: buybook
#pop_level = [30, float('inf')] # group: buybook
# prediction_date 的含义为：在帖子发布 prediction_date 时间后，开始预测
# target_date 的含义为：预测在 target_date 处的评论数量
# 以上两个参数可以调节
# 设置采样的间隔
gaptime = timedelta(hours=5)
prediction_date = timedelta(hours=10*5)
response_time = timedelta(hours=50)
target_date = prediction_date + response_time
# 计算每个topic在prediction_date前会有多少个interval
num_feature = int(prediction_date.total_seconds() / gaptime.total_seconds())
print 'Number of features: ', num_feature
alpha = 1.5
percentage_threshold = 0.7
print 'Generating training and test dataset...'
dataset, comment_count_dataset, Bao_dataset, category_count_list = prepare_dataset(group_id, \
topic_list, gaptime, pop_level, prediction_date, target_date, alpha, percentage_threshold)
# 保存那些经过筛选的topic id
#save_filtered_topics(group_id, dataset)
#print 'Ploting factor propagation'
#factor_propagation_plot(dataset, num_feature)
#topic_propagation_plot(dataset, num_feature)
#return
# 调整所有帖子的顺序
# 在调试阶段，暂且不shuffle dataset，避免每次结果都不一样
#shuffle(dataset)
print 'Down-sampling the datasets...'
dataset, comment_count_dataset, Bao_dataset, category_count_list = down_sampling_dataset(dataset, \
comment_count_dataset, Bao_dataset, category_count_list)
total = len(dataset)
train_cnt = total * 4 / 5
train_set = dataset[:train_cnt]
test_set = dataset[train_cnt:]
print 'Training: %d, Test: %d' % (train_cnt, total-train_cnt)
print 'Category 0: %d, Category 1: %d ' % (category_count_list[0] , category_count_list[1])
print 'Imbalance ratio: ', category_count_list[0] * 1.0 / category_count_list[1]
#num_level = len(pop_level)
#raw_input()
#import ipdb
#ipdb.set_trace()
print 'The proposed model:'
k = 3
num_level = 2
num_factor = len(train_set[0][1][1])
print 'Classify test instances...'
y_true, y_pred, comment_true, comment_pred, give_up_list, prediction_list = classify(train_set, test_set, k, num_level)
# evaluate results
print 'Number of give-ups: ', len(give_up_list)
classification_evaluation(y_true, y_pred)
level_MSE_evaluation(y_true, y_pred)
#save_predictions(prediction_list, y_pred, factor_name = 'num_authors')
#save_predictions(prediction_list, y_true, factor_name = 'all')
comment_RSE_evaluation(comment_true, comment_pred)
#print 'The class prior:', prior_score
from svm_model import svm_model
print 'Building a svm model...'
y_true, y_pred = svm_model(train_set, test_set)
classification_evaluation(y_true, y_pred)
# 查看对于不同的factor，它们在不同的ratio上的预测结果
#from utils import ratio_accuracy_distribution_plot
#ratio_accuracy_distribution_plot(y_true, y_pred, test_set, group_id, factor_name='tree_link_density')
# S-H model
print '\nThe S-H model:'
baseline_train_set = comment_count_dataset[:train_cnt]
baseline_test_set = comment_count_dataset[train_cnt:]
y_true, y_pred, comment_true_cnt, comment_pred_cnt = SH_model(baseline_train_set, baseline_test_set, alpha)
# drop some intances with cat = 0
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
# level wise classification
classification_evaluation(y_true, y_pred)
level_MSE_evaluation(y_true, y_pred)
print '\nML model:'
y_true, y_pred, comment_true_cnt, comment_pred_cnt = ML_model(baseline_train_set, baseline_test_set, num_feature, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
print '\nMLR model:'
y_true, y_pred, comment_true_cnt, comment_pred_cnt = MLR_model(baseline_train_set, baseline_test_set, num_feature, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
print '\nkNN method:'
k = 1
y_true, y_pred, comment_true_cnt, comment_pred_cnt = knn_method(train_set, test_set, k, num_feature, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
# level wise classification
classification_evaluation(y_true, y_pred)
print "\nBao's method:"
Bao_train_set = Bao_dataset[:train_cnt]
Bao_test_set = Bao_dataset[train_cnt:]
y_true, y_pred, comment_true_cnt, comment_pred_cnt = Bao_method(Bao_train_set, Bao_test_set, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
def main(group_id, topic_list, threshold_p, prediction_date_tr, response_time_delta, gaptime_n, best_k):
# 设置两个自由参数值，由外部传入
percentage_threshold = threshold_p
prediction_date = timedelta(hours=prediction_date_tr)
response_time = timedelta(hours=response_time_delta)
# set the pre-computed popularity level
# 未来的最大评论数可能超过pop_level的最大值
# 注意：这里将最小的popularity值，即0，忽略了
#pop_level = [8, 13, 23, 43, float('inf')] # group: zhuangb
pop_level = [25, 50, float('inf')] # group: zhuangb
#pop_level = [25, 50, float('inf')] # group: buybook
#pop_level = [30, float('inf')] # group: buybook
# prediction_date 的含义为：在帖子发布 prediction_date 时间后，开始预测
# target_date 的含义为：预测在 target_date 处的评论数量
# 以上两个参数可以调节
# 设置采样的间隔
gaptime = timedelta(hours=gaptime_n)
#prediction_date = timedelta(hours=10*3)
#response_time = timedelta(hours=24) # 已经作为参数传递
target_date = prediction_date + response_time
# 计算每个topic在prediction_date前会有多少个interval
num_feature = int(prediction_date.total_seconds() / gaptime.total_seconds())
print 'Number of features: ', num_feature
#percentage_threshold = 0.7
alpha = 1/percentage_threshold
#"""
print 'Generating training and test dataset...'
dataset, comment_count_dataset, Bao_dataset, category_count_list = prepare_dataset(group_id, \
topic_list, gaptime, pop_level, prediction_date, target_date, alpha, percentage_threshold)
# 保存那些经过筛选的topic id
#save_filtered_topics(group_id, dataset)
#print 'Ploting factor propagation'
#factor_propagation_plot(dataset, num_feature)
#topic_propagation_plot(dataset, num_feature)
#return
print 'Down-sampling the datasets...'
dataset, comment_count_dataset, Bao_dataset, category_count_list = down_sampling_dataset(dataset, \
comment_count_dataset, Bao_dataset, category_count_list)
# 调整所有帖子的顺序
# 在调试阶段，暂且不shuffle dataset，避免每次结果都不一样
#shuffle(dataset)
# 注意：每次使用的数据集是不同的
total = len(dataset)
train_cnt = total * 4 / 5
train_set = dataset[:train_cnt]
test_set = dataset[train_cnt:]
print 'Training: %d, Test: %d' % (train_cnt, total-train_cnt)
print 'Category 0: %d, Category 1: %d ' % (category_count_list[0] , category_count_list[1])
print 'Imbalance ratio: ', category_count_list[0] * 1.0 / category_count_list[1]
#num_level = len(pop_level)
#save_filtered_topics(group_id, dataset)
#raw_input()
from MDT_method import prepare_MDT_dataset
#prepare_MDT_dataset(train_set, 'MDT_train.pickle')
#prepare_MDT_dataset(test_set, 'MDT_test.pickle')
#return
k = best_k
num_level = 2
num_factor = len(train_set[0][1][1])
print 'The proposed model:'
#print 'Caculating class prior score...'
#prior_score = np.ones((num_factor, num_level)) # 初始化
#prior_score = caculate_class_prior_confidence_score(train_set, k, num_level = 2)
#print prior_score; raw_input()
print 'Caculating instance prior score...'
prior_score = -1
mutual_knn_graph_list = None
#prior_score = caculate_instance_prior_confidence_score(train_set, k, num_level = 2) # for instance_prior_weighting3.py
topic_popularity, prior_score, mutual_knn_graph_list = caculate_instance_prior_confidence_score(train_set, test_set, k, num_factor, num_level = 2) # for IPW_mutual_knn.py
# 保存prior-score，train dataset，test-dataset
#save_intermediate_results(train_set, test_set, comment_count_dataset, Bao_dataset, category_count_list, topic_popularity, prior_score, mutual_knn_graph_list)
#"""
#print 'Loading train_set, test_set, comment_count_dataset, ... and prior_score...'
#train_set, test_set, comment_count_dataset, Bao_dataset, category_count_list, topic_popularity, prior_score, mutual_knn_graph_list = load_intermediate_results()
#train_cnt = len(train_set)
#k = best_k; num_level=2; num_factor = len(train_set[0][1][1])
#factor_name_list = ['current_comment_count', 'num_authors', 'tree_density', 'reply_density'] # 需要考察的factor变量
#factor_propagation_plot(group_id, train_set+test_set, num_feature, category_count_list, range(4), factor_name_list)
#return
print 'Parameter set:'
print 'Gap time: ', gaptime
print 'Prediction date(in hours):', prediction_date.total_seconds() / 3600
print 'Response time(in hours):', response_time.total_seconds() / 3600
print 'percentage_threshold: ', percentage_threshold
print 'k = ', k
# TODO：测试是否过拟合
#test_set = train_set # 将训练集作为测试集，查看是否过拟合
print 'Classify test instances...'
y_true, y_pred, comment_true, comment_pred, give_up_list, prediction_list, factor_prediction = \
classify(train_set, test_set, k, num_factor, num_level, prior_score, topic_popularity, mutual_knn_graph_list)
# evaluate results
print 'Number of give-ups: ', len(give_up_list)
IPW_acc = classification_evaluation(y_true, y_pred)
level_MSE_evaluation(y_true, y_pred)
#save_predictions(prediction_list, y_pred, factor_name = 'fourfactor')
#save_predictions(prediction_list, y_true, factor_name = 'all')
comment_RSE_evaluation(comment_true, comment_pred)
#print 'The class prior:', prior_score
print 'Single factor and simple vote prediction result:'
single_factor_acc = single_factor_prediction(y_true, factor_prediction)
from svm_model import svm_model
print 'Building a svm model...'
y_true, y_pred = svm_model(train_set, test_set)
classification_evaluation(y_true, y_pred)
# 查看对于不同的factor，它们在不同的ratio上的预测结果
from utils import ratio_accuracy_distribution_plot
#ratio_accuracy_distribution_plot(y_true, y_pred, test_set, group_id, factor_name='tree_link_density')
# S-H model
print '\nThe S-H model:'
baseline_train_set = comment_count_dataset[:train_cnt]
baseline_test_set = comment_count_dataset[train_cnt:]
y_true, y_pred, comment_true_cnt, comment_pred_cnt = SH_model(baseline_train_set, baseline_test_set, alpha)
# drop some intances with cat = 0
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
# level wise classification
classification_evaluation(y_true, y_pred)
level_MSE_evaluation(y_true, y_pred)
print '\nML model:'
y_true, y_pred, comment_true_cnt, comment_pred_cnt = ML_model(baseline_train_set, baseline_test_set, num_feature, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
print '\nMLR model:'
y_true, y_pred, comment_true_cnt, comment_pred_cnt = MLR_model(baseline_train_set, baseline_test_set, num_feature, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
print '\nkNN method:'
knn_k = 1
y_true, y_pred, comment_true_cnt, comment_pred_cnt = knn_method(train_set, test_set, knn_k, num_feature, alpha)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
# level wise classification
classification_evaluation(y_true, y_pred)
print "\nBao's method:"
Bao_train_set = Bao_dataset[:train_cnt]
Bao_test_set = Bao_dataset[train_cnt:]
print 'With link density:'
y_true, y_pred, comment_true_cnt, comment_pred_cnt = Bao_method(Bao_train_set, Bao_test_set, alpha, version = 1)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
print 'With diffusion depth:'
y_true, y_pred, comment_true_cnt, comment_pred_cnt = Bao_method(Bao_train_set, Bao_test_set, alpha, version = 2)
comment_RSE_evaluation(comment_true_cnt, comment_pred_cnt)
classification_evaluation(y_true, y_pred)
return IPW_acc, single_factor_acc # 返回正确率