def generate_graph(fname, ttype, utype):
"""
Make Daily Graph
:param fname:
:param ttype:
:param utype:
:return:
"""
# Basic Setting
sns.set(style='darkgrid')
myfont = fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')
path = "../Data/Graph/Statistic_Graph/Day/" + fname[6:-2]
if not os.path.isdir(path):
os.mkdir(path)
color_array = ['Blue', 'Red', 'Green']
label_array = ['Borrow', 'Return', 'Total']
# Load data and plot
borrow_data, return_data = LoadData.load_station_count(fname, ttype, utype)
# print('borrow_data\n', borrow_data.head())
# print('return_data\n', return_data.head())
# x=input()
header = list(borrow_data.columns)
x_data = np.array(borrow_data.index)
print('x_data', x_data)
x_data = np.array([i for i in range(24)])
for col in header:
fig, ax = plt.subplots(figsize=(8, 6), dpi=100)
y1_data = borrow_data[col].values.T
y2_data = return_data[col].values.T
y3_data = y1_data + y2_data
ax.plot(x_data, y1_data, color=color_array[0], label=label_array[0])
ax.plot(x_data, y2_data, color=color_array[1], label=label_array[1])
ax.plot(x_data, y3_data, color=color_array[2], label=label_array[2])
plt.title(col, fontproperties=myfont)
plt.xlabel('Time')
plt.ylabel('Count')
plt.xticks(np.arange(24), borrow_data.index, rotation=45)
if np.sum(y3_data) == 0:
plt.ylim(ymin=0)
else:
plt.ylim(ymin=0, ymax=np.max(y3_data))
# Put a nicer background color on the legend.
legend = ax.legend(loc='upper right')
legend.get_frame().set_facecolor('C0')
try:
photo_path = path + '/' + col + '.png'
plt.savefig(photo_path)
except FileNotFoundError:
col = col.replace('/', '-')
photo_path = path + '/' + col + '.png'
plt.savefig(photo_path)
plt.ion()
plt.pause(1)
plt.close()
def week_time_series(fname, ttype, utype):
"""
以一周 7天去統計每一小時區間的使用次數
開始天數往後推 7天, 第一天 2015-01-01 是禮拜四
以 day_time_series 計算完的 csv 檔去產生新的 csv
"""
header = ['Thu', 'Fri', 'Sat', 'Sun', 'Mon', 'Tue', 'Wed']
idx = []
pd_borrow_data, pd_return_data = (pd.DataFrame() for _ in range(2))
for file, days in zip(fname, header):
borrow_data, return_data = LoadData.load_station_count(
file, ttype, utype)
idx += [(days, ) + make_tuple(x) for x in borrow_data.index]
pd_borrow_data = pd.concat((pd_borrow_data, borrow_data),
axis=0,
ignore_index=True)
pd_return_data = pd.concat((pd_return_data, return_data),
axis=0,
ignore_index=True)
pd_borrow_data.index = idx
pd_return_data.index = idx
# print('pd_borrow_data\n', pd_borrow_data.head())
# print('pd_return_data\n', pd_return_data.head())
name = fname[0][6:16] + '~' + fname[-1][6:16]
Export.week_station_count(pd_borrow_data, name, utype[0])
Export.week_station_count(pd_return_data, name, utype[1])
def month_time_series(fname, ttype, utype):
"""
以一月的天數去統計每天的使用次數
第一個月是 2015-01 ~ 2017-05
以 day_time_series 計算完的 csv 檔去產生新的 csv
"""
target_timestamp = np.array([])
start_date = datetime.datetime(2015, 1, 1)
end_date = datetime.datetime(2017, 5, 31)
for dt in rrule(MONTHLY, dtstart=start_date, until=end_date):
target_timestamp = np.append(target_timestamp,
dt.strftime("%Y-%m"))
# print('target_timestamp\n', target_timestamp)
for timestamp in target_timestamp:
element = [x for x in fname if x.find(timestamp) != -1]
np_borrow, np_return = (np.array([]) for _ in range(2))
idx = np.array([])
columns = np.array([])
for field in element:
idx = np.append(idx, field[6:16])
borrow_data, return_data = LoadData.load_station_count(
field, ttype, utype)
if columns.size == 0:
columns = borrow_data.columns
# np_data1-> sum of the borrow_data
# np_data2-> sum of the return_data
np_data1 = np.sum(borrow_data.values, axis=0).reshape(1, -1)
np_data2 = np.sum(return_data.values, axis=0).reshape(1, -1)
if np_borrow.size == 0:
np_borrow = np_data1
else:
np_borrow = np.concatenate((np_borrow, np_data1), axis=0)
if np_return.size == 0:
np_return = np_data2
else:
np_return = np.concatenate((np_return, np_data2), axis=0)
# print('np_borrow\n', np_borrow, np_borrow.shape)
# print('np_return\n', np_return, np_return.shape)
pd_borrow = pd.DataFrame(np_borrow, columns=columns, index=idx)
pd_return = pd.DataFrame(np_return, columns=columns, index=idx)
Export.month_station_count(pd_borrow, timestamp, utype[0])
Export.month_station_count(pd_return, timestamp, utype[1])
def graph_by_hour(fname, ttype, utype):
"""
Month Graph(Build One Month -> 24 hours on each day)
Ubike-DataMining\\Data\\NewUbike\\UbikeStatistic\\Day\\
"""
# Basic Setting
header = [x[14:16] for x in fname]
sns.set(style='darkgrid')
myfont = fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')
color_array = ['Blue', 'Red', 'Green']
label_array = ['Borrow', 'Return', 'Total']
line_size = 0.7
# Open or Create a folder
name = fname[0][6:13]
path = "../Data/Graph/Statistic_Graph/Month(hour)/" + name
if not os.path.isdir(path):
os.mkdir(path)
# Load data and plot
# x_data = np.array([i for i in range(24 * len(header))])
pd_borrow_data, pd_return_data = (pd.DataFrame() for _ in range(2))
for file in fname:
borrow_data, return_data = LoadData.load_station_count(
file, ttype, utype)
pd_borrow_data = pd.concat((pd_borrow_data, borrow_data), axis=0)
pd_return_data = pd.concat((pd_return_data, return_data), axis=0)
for col in pd_borrow_data.columns:
y1_data = pd_borrow_data[col].values
y2_data = pd_return_data[col].values
y3_data = y1_data + y2_data
f, axarr = plt.subplots(3, 1, sharex='all', figsize=(16, 8), dpi=100)
axarr[0].plot(y1_data,
color=color_array[0],
label=label_array[0],
linewidth=line_size)
axarr[1].plot(y2_data,
color=color_array[1],
label=label_array[1],
linewidth=line_size)
axarr[2].plot(y3_data,
color=color_array[2],
label=label_array[2],
linewidth=line_size)
# Graph Setting
# plt.tight_layout()
axarr[0].set_title(col + '(' + name + ')', fontproperties=myfont)
plt.xticks(np.arange(0, 24 * len(header), 24),
header,
rotation=0,
fontsize=12)
for sub_plot in axarr:
sub_plot.legend(loc='upper right')
sub_plot.set_ylim(
ymin=0) if np.sum(y3_data) == 0 else sub_plot.set_ylim(
ymin=0, ymax=np.max(y3_data))
sub_plot.set_ylabel('次數', fontproperties=myfont)
try:
photo_path = path + '/' + col + '.png'
plt.savefig(photo_path)
except FileNotFoundError:
col = col.replace('/', '-')
photo_path = path + '/' + col + '.png'
plt.savefig(photo_path)
# plt.ion()
# plt.pause(1)
plt.close()
start = time.time()
# 小波分解的層數
layer = 15
# 起始年和到哪年為止
syear = 2015
eyear = 2016
timeseries = generate_target_timeseries(syear, eyear)
# 讀檔，將每個csv檔案的資料取出
for series, target_timestamp in timeseries.items():
total_borrow_data = pd.DataFrame()
total_return_data = pd.DataFrame()
for target in target_timestamp:
borrow_data, return_data = LoadData.load_station_count(
target, 'Day', ['BorrowStation', 'ReturnStation'])
total_borrow_data = pd.concat((total_borrow_data, borrow_data), axis=0)
total_return_data = pd.concat((total_return_data, return_data), axis=0)
#
print(total_borrow_data.shape)
print(total_return_data.shape)
# 進行小波分解(0 ~ N 層)
# 並做出相對應的小波分解後的視覺化圖
algorithm = pywt.Wavelet('db2')
wavelet = WaveletTransform(total_borrow_data,
total_return_data,
int(layer),
algorithm,
interval=series[0])
wavelet.fit_transform()
def generate_graph(fname, ttype, utype):
"""
Week Graph(Monday~Sunday)
如果要畫一周圖的話，可以每次都先讀入 7份csv檔案來作圖
:param fname: file name
:param ttype: Week
:param utype: Borrow, Return
:return:
"""
# Basic Setting
header = ['Thu', 'Fri', 'Sat', 'Sun', 'Mon', 'Tue', 'Wed']
sns.set(style='darkgrid')
myfont = fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')
path = "../Data/Graph/Statistic_Graph/Week/" + fname[0][
6:16] + '~' + fname[-1][6:16]
if not os.path.isdir(path):
os.mkdir(path)
color_array = ['Blue', 'Red', 'Green']
label_array = ['Borrow', 'Return', 'Total']
# Load data and plot
x_data = np.array([i for i in range(24 * len(header))])
pd_borrow_data, pd_return_data = (pd.DataFrame() for _ in range(2))
for file in fname:
borrow_data, return_data = LoadData.load_station_count(
file, ttype, utype)
pd_borrow_data = pd.concat((pd_borrow_data, borrow_data), axis=0)
pd_return_data = pd.concat((pd_return_data, return_data), axis=0)
for col in pd_borrow_data.columns:
fig, ax = plt.subplots(figsize=(16, 8), dpi=100)
y1_data = pd_borrow_data[col].values
y2_data = pd_return_data[col].values
y3_data = y1_data + y2_data
ax.plot(x_data, y1_data, color=color_array[0], label=label_array[0])
ax.plot(x_data, y2_data, color=color_array[1], label=label_array[1])
ax.plot(x_data, y3_data, color=color_array[2], label=label_array[2])
plt.title(col + '(' + fname[0][6:16] + '~' + fname[-1][6:16] + ')',
fontproperties=myfont)
plt.xlabel('時間軸', fontproperties=myfont)
plt.ylabel('租借次數', fontproperties=myfont)
plt.xticks(np.arange(0, 24 * len(header), 24),
header,
rotation=45,
fontsize=12)
# plt.xticks(range(len(header)), rotation=45)
if np.sum(y3_data) == 0:
plt.ylim(ymin=0)
else:
plt.ylim(ymin=0, ymax=np.max(y3_data))
# Put a nicer background color on the legend.
legend = ax.legend(loc='upper right')
legend.get_frame().set_facecolor('C0')
# manager = plt.get_current_fig_manager()
# manager.window.showMaximized()
try:
photo_path = path + '/' + col + '.png'
plt.savefig(photo_path)
except FileNotFoundError:
col = col.replace('/', '-')
photo_path = path + '/' + col + '.png'
plt.savefig(photo_path)
# plt.ion()
# plt.pause(1)
plt.close()
