def disp_gap_by_district_type(self):
df = self.gapdf
data_dir = g_singletonDataFilePath.getTrainDir()
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_poi.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
temp_df = dumpload.load()
else:
poi_dict = self.get_district_type_dict()
temp_df = self.X_y_Df[['start_district_id']].apply(self.find_poi,axis = 1, poi_dict=poi_dict)
dumpload.dump(temp_df)
df = pd.concat([df, temp_df], axis=1)
dt_list = self.get_district_type_list()
size = len(dt_list)
col_len = 4
row_len = 7
# col_len = row_len = int(math.ceil(math.sqrt(size)))
# count = 1
_, axarr = plt.subplots(row_len, col_len, sharex=True, sharey=True)
for row in range(row_len):
for col in range(col_len):
index = row * col_len + col
if index >= size:
break
item = dt_list[index]
axarr[row, col].scatter(df[item], df['gap'])
axarr[row, col].set_ylabel('Gap')
axarr[row, col].set_xlabel(item)
return
def get_history_data_dict(self):
"""
indexes for quick search
key = 'start_district_id','time_id'
value = 'gap
its data includes those from train, test1, test2.
"""
t0 = time()
filename = "../data_preprocessed/" + 'traintest_history_data.dict.pickle'
dumpload = DumpLoad( filename)
if dumpload.isExisiting():
return dumpload.load()
test1data_df = ExploreOrder().load_gapdf(g_singletonDataFilePath.getTest1Dir())
test2data_df = ExploreOrder().load_gapdf(g_singletonDataFilePath.getTest2Dir())
traindata_df = ExploreOrder().load_gapdf(g_singletonDataFilePath.getTrainDir())
df = pd.concat([traindata_df, test1data_df,test2data_df], axis=0)
self.__fileter_earlier_date(df)
res_dict = self.__generate_dict(df)
dumpload.dump(res_dict)
print "dump weather dict:", round(time()-t0, 3), "s"
return res_dict
def disp_gap_bytraffic(self):
df = self.gapdf
data_dir = g_singletonDataFilePath.getTrainDir()
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_prevtraffic.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
temp_df = dumpload.load()
else:
traffic_dict = self.get_traffic_dict(data_dir)
temp_df = self.X_y_Df[['start_district_id', 'time_slotid']].apply(self.find_prev_traffic,axis = 1, traffic_dict=traffic_dict, pre_num = 3)
dumpload.dump(temp_df)
df = pd.concat([df, temp_df], axis=1)
by_traffic = df.groupby('traffic1')
x=[]
y=[]
for name, group in by_traffic:
x.append(name)
y.append(group['gap'].mean())
plt.scatter(x,y)
return
def disp_gap_bytraffic(self):
df = self.gapdf
data_dir = g_singletonDataFilePath.getTrainDir()
dumpfile_path = '../data_preprocessed/' + data_dir.split(
'/')[-2] + '_prevtraffic.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
temp_df = dumpload.load()
else:
traffic_dict = self.get_traffic_dict(data_dir)
temp_df = self.X_y_Df[['start_district_id', 'time_slotid'
]].apply(self.find_prev_traffic,
axis=1,
traffic_dict=traffic_dict,
pre_num=3)
dumpload.dump(temp_df)
df = pd.concat([df, temp_df], axis=1)
by_traffic = df.groupby('traffic1')
x = []
y = []
for name, group in by_traffic:
x.append(name)
y.append(group['gap'].mean())
plt.scatter(x, y)
return
def __normalize(self):
self.X_train = self.X_train.astype(np.float32)
self.X_val = self.X_val.astype(np.float32)
self.X_test = self.X_test.astype(np.float32)
mean_image = np.mean(self.X_train, axis=0)
std_image = np.std(self.X_train, axis=0)
self.X_train = (self.X_train - mean_image) / std_image
self.X_val = (self.X_val - mean_image) / std_image
self.X_test = (self.X_test - mean_image) / std_image
dumpload = DumpLoad('../data/meanstdimage.pickle')
if not dumpload.isExisiting():
dumpload.dump((mean_image, std_image))
# self.X_test -= mean_image
# self.X_train = ((self.X_train - 128)/128.0)
# self.X_val = ((self.X_val - 128)/128.0)
# self.X_test = ((self.X_val - 128)/128.0)
# sc = MinMaxScaler()
# sc.fit(self.X_train)
# self.x_train= sc.transform(self.X_train)
# self.X_val= sc.transform(self.X_val)
# self.X_test= sc.transform(self.X_test)
return
def get_history_data_dict(self):
"""
indexes for quick search
key = 'start_district_id','time_id'
value = 'gap
its data includes those from train, test1, test2.
"""
t0 = time()
filename = "../data_preprocessed/" + 'traintest_history_data.dict.pickle'
dumpload = DumpLoad(filename)
if dumpload.isExisiting():
return dumpload.load()
test1data_df = ExploreOrder().load_gapdf(
g_singletonDataFilePath.getTest1Dir())
test2data_df = ExploreOrder().load_gapdf(
g_singletonDataFilePath.getTest2Dir())
traindata_df = ExploreOrder().load_gapdf(
g_singletonDataFilePath.getTrainDir())
df = pd.concat([traindata_df, test1data_df, test2data_df], axis=0)
self.__fileter_earlier_date(df)
res_dict = self.__generate_dict(df)
dumpload.dump(res_dict)
print "dump weather dict:", round(time() - t0, 3), "s"
return res_dict
def add_history_data(self,data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_history_data.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
temp_dict = self.get_history_data_dict()
df = self.X_y_Df[['start_district_id', 'time_id']].apply(self.find_history_data, axis = 1, history_dict = temp_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
return
def add_district_gap_sum(self):
dumpfile_path = '../data_preprocessed/' +'training_data_district_gap_sum.dict.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
district_gap_sum_dict = dumpload.load()
else:
district_gap_sum_dict = self.X_y_Df.groupby('start_district_id')['gap'].sum().to_dict()
dumpload.dump(district_gap_sum_dict)
self.X_y_Df["district_gap_sum"] = self.X_y_Df["start_district_id"].map(district_gap_sum_dict)
return
def add_pre_gaps(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_prevgap.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
gap_dict = self.get_gap_dict(data_dir)
df = self.X_y_Df[['start_district_id', 'time_slotid']].apply(self.find_prev_gap, axis = 1, pre_num = 3, gap_dict = gap_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
return
def __add_poi(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_poi.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
poi_dict = self.get_district_type_dict()
df = self.X_y_Df[['start_district_id']].apply(self.find_poi,axis = 1, poi_dict=poi_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
return
def add_district_gap_sum(self):
dumpfile_path = '../data_preprocessed/' + 'training_data_district_gap_sum.dict.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
district_gap_sum_dict = dumpload.load()
else:
district_gap_sum_dict = self.X_y_Df.groupby(
'start_district_id')['gap'].sum().to_dict()
dumpload.dump(district_gap_sum_dict)
self.X_y_Df["district_gap_sum"] = self.X_y_Df["start_district_id"].map(
district_gap_sum_dict)
return
def add_prev_weather(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_prevweather.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
weather_dict = self.get_weather_dict(data_dir)
df = self.X_y_Df['time_slotid'].apply(self.find_prev_weather_mode, weather_dict=weather_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
self.add_rain_check()
return
def add_history_data(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split(
'/')[-2] + '_history_data.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
temp_dict = self.get_history_data_dict()
df = self.X_y_Df[['start_district_id',
'time_id']].apply(self.find_history_data,
axis=1,
history_dict=temp_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
return
def add_pre_gaps(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split(
'/')[-2] + '_prevgap.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
gap_dict = self.get_gap_dict(data_dir)
df = self.X_y_Df[['start_district_id',
'time_slotid']].apply(self.find_prev_gap,
axis=1,
pre_num=3,
gap_dict=gap_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
return
def add_prev_weather(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split(
'/')[-2] + '_prevweather.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
weather_dict = self.get_weather_dict(data_dir)
df = self.X_y_Df['time_slotid'].apply(self.find_prev_weather_mode,
weather_dict=weather_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
self.add_rain_check()
return
def __add_poi(self, data_dir):
dumpfile_path = '../data_preprocessed/' + data_dir.split(
'/')[-2] + '_poi.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
df = dumpload.load()
else:
poi_dict = self.get_district_type_dict()
df = self.X_y_Df[['start_district_id']].apply(self.find_poi,
axis=1,
poi_dict=poi_dict)
dumpload.dump(df)
self.X_y_Df = pd.concat([self.X_y_Df, df], axis=1)
return
def get_traffic_dict(self, data_dir):
t0 = time()
filename = '../data_raw/' + data_dir.split(
'/')[-2] + '_traffic.csv.dict.pickle'
dumpload = DumpLoad(filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_trafficdf(data_dir)
for _, row in df.iterrows():
resDict[tuple(row[['start_district_id',
'time_slotid']].tolist())] = row['traffic']
dumpload.dump(resDict)
print "dump traffic dict:", round(time() - t0, 3), "s"
return resDict
def disp_names(self, sorted_inds, probabilities, include_background=True):
dump_load = DumpLoad("../../data/imagenet/imagenet_labels_dict.pickle")
if dump_load.isExisiting():
names = dump_load.load()
else:
names = imagenet.create_readable_names_for_imagenet_labels()
dump_load.dump(names)
for i in range(5):
index = sorted_inds[i]
if include_background:
print('Probability %0.2f%% => [%s]' %
(probabilities[index], names[index]))
else:
print('Probability %0.2f%% => [%s]' %
(probabilities[index], names[index + 1]))
return
def get_gap_meanmedian_dict(self):
data_dir = g_singletonDataFilePath.getTrainDir()
filename = data_dir + 'order_data/temp/gap_meanmedian.dict.pickle'
dumpload = DumpLoad( filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_gapdf(data_dir)
grps = df.groupby(['start_district_id','time_id'])
for name, row in grps:
resDict[name] = row['gap'].tolist()
# resDict[name] = [i for i in row['gap'].tolist() if i !=0]
dumpload.dump(resDict)
return resDict
def get_gap_meanmedian_dict(self):
data_dir = g_singletonDataFilePath.getTrainDir()
filename = data_dir + 'order_data/temp/gap_meanmedian.dict.pickle'
dumpload = DumpLoad(filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_gapdf(data_dir)
grps = df.groupby(['start_district_id', 'time_id'])
for name, row in grps:
resDict[name] = row['gap'].tolist()
# resDict[name] = [i for i in row['gap'].tolist() if i !=0]
dumpload.dump(resDict)
return resDict
def get_weather_dict(self,data_dir):
t0 = time()
filename = '../data_raw/' + data_dir.split('/')[-2] + '_weather.csv.dict.pickle'
dumpload = DumpLoad( filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_weatherdf(data_dir)
for index, row in df.iterrows():
resDict[row['time_slotid']] = (index, row['weather'], row['temparature'], row['pm25'])
for name, group in df.groupby('time_date'):
resDict[name] = (-1, mode(group['weather'])[0][0], mode(group['temparature'])[0][0], mode(group['pm25'])[0][0])
dumpload.dump(resDict)
print "dump weather dict:", round(time()-t0, 3), "s"
return resDict
def disp_gap_by_district_type(self):
df = self.gapdf
data_dir = g_singletonDataFilePath.getTrainDir()
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_poi.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
temp_df = dumpload.load()
else:
poi_dict = self.get_district_type_dict()
temp_df = self.X_y_Df[['start_district_id']].apply(self.find_poi,axis = 1, poi_dict=poi_dict)
dumpload.dump(temp_df)
df = pd.concat([df, temp_df], axis=1)
dt_list = self.get_district_type_list()
size = len(dt_list)
col_len = 4
row_len = 7
# col_len = row_len = int(math.ceil(math.sqrt(size)))
# count = 1
_, axarr = plt.subplots(row_len, col_len, sharex=True, sharey=True)
for row in range(row_len):
for col in range(col_len):
index = row * col_len + col
if index >= size:
break
item = dt_list[index]
axarr[row, col].scatter(df[item], df['gap'])
axarr[row, col].set_ylabel('Gap')
axarr[row, col].set_xlabel(item)
# axarr[row, col].set_title('POI/Gap Correlation')
# for item in dt_list:
# plt.subplot(row_len, col_len, count)
# plt.scatter(df[item], df['gap'])
# plt.ylabel('Gap')
# plt.xlabel('POI')
# count += 1
# plt.title('POI/Gap Correlation')
return
def get_gap_dict(self, data_dir):
"""
indexes for quick search
key = 'start_district_id','time_slotid
value = gap
"""
t0 = time()
filename = "../data_preprocessed/" + data_dir.split('/')[-2] + '_gap.csv.dict.pickle'
dumpload = DumpLoad( filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_gapdf(data_dir)
for _, row in df.iterrows():
resDict[tuple(row[['start_district_id','time_slotid']].tolist())] = row['gap']
dumpload.dump(resDict)
print "dump gapdict:", round(time()-t0, 3), "s"
return resDict
def disp_gap_byweather(self):
df = self.gapdf
data_dir = g_singletonDataFilePath.getTrainDir()
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_prevweather.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
temp_df = dumpload.load()
else:
weather_dict = self.get_weather_dict(data_dir)
temp_df = self.X_y_Df['time_slotid'].apply(self.find_prev_weather_mode, weather_dict=weather_dict)
dumpload.dump(temp_df)
df = pd.concat([df, temp_df], axis=1)
gaps_mean = df.groupby('preweather')['gap'].mean()
gaps_mean.plot(kind='bar')
plt.ylabel('Mean of gap')
plt.xlabel('Weather')
plt.title('Weather/Gap Correlation')
return
def disp_gap_byweather(self):
df = self.gapdf
data_dir = g_singletonDataFilePath.getTrainDir()
dumpfile_path = '../data_preprocessed/' + data_dir.split('/')[-2] + '_prevweather.df.pickle'
dumpload = DumpLoad(dumpfile_path)
if dumpload.isExisiting():
temp_df = dumpload.load()
else:
weather_dict = self.get_weather_dict(data_dir)
temp_df = self.X_y_Df['time_slotid'].apply(self.find_prev_weather_mode, weather_dict=weather_dict)
dumpload.dump(temp_df)
df = pd.concat([df, temp_df], axis=1)
gaps_mean = df.groupby('preweather')['gap'].mean()
gaps_mean.plot(kind='bar')
plt.ylabel('Mean of gap')
plt.xlabel('Weather')
plt.title('Weather/Gap Correlation')
return
def get_weather_dict(self, data_dir):
t0 = time()
filename = '../data_raw/' + data_dir.split(
'/')[-2] + '_weather.csv.dict.pickle'
dumpload = DumpLoad(filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_weatherdf(data_dir)
for index, row in df.iterrows():
resDict[row['time_slotid']] = (index, row['weather'],
row['temparature'], row['pm25'])
for name, group in df.groupby('time_date'):
resDict[name] = (-1, mode(group['weather'])[0][0],
mode(group['temparature'])[0][0],
mode(group['pm25'])[0][0])
dumpload.dump(resDict)
print "dump weather dict:", round(time() - t0, 3), "s"
return resDict
def get_gap_dict(self, data_dir):
"""
indexes for quick search
key = 'start_district_id','time_slotid
value = gap
"""
t0 = time()
filename = "../data_preprocessed/" + data_dir.split(
'/')[-2] + '_gap.csv.dict.pickle'
dumpload = DumpLoad(filename)
if dumpload.isExisiting():
return dumpload.load()
resDict = {}
df = self.load_gapdf(data_dir)
for _, row in df.iterrows():
resDict[tuple(row[['start_district_id',
'time_slotid']].tolist())] = row['gap']
dumpload.dump(resDict)
print("dump gapdict:", round(time() - t0, 3), "s")
return resDict
dictionary[word] = len(dictionary)
data = list()
unk_count = 0
for word in words:
if word in dictionary:
index = dictionary[word]
else:
index = 0 # dictionary['UNK']
unk_count = unk_count + 1
data.append(index)
count[0][1] = unk_count
reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
return data, count, dictionary, reverse_dictionary
rawdata = DumpLoad('./data/rawdata.pickle')
if not rawdata.isExisiting():
# data, count, dictionary, reverse_dictionary = build_dataset(words)
rawdata.dump(build_dataset(words))
data, count, dictionary, reverse_dictionary = rawdata.load()
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10])
del words # Hint to reduce memory.
data_index = 0
def generate_batch(batch_size, num_skips, skip_window):
global data_index
assert batch_size % num_skips == 0