def sorted_ob_fo_muti_model(ob, fo_list, save_path=None):
'''
sorted_ob_fo_muti_model 多模式下先对数据排序，然后在画多个折线图子图
:param ob:一个实况数据 类型 dataframe
:param fo_list:多模式预测数据 列表 类型list list中的类型是dataframe
每个dataframe 中的最后一列列名不能相同，表示时空数据的列为在前，列名相同
:param save_path:保存地址
:return:
'''
fo_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_list)
ob = meger_df_data.iloc[:, -1].values
data_len = len(fo_list)
plt.figure(figsize=[10 * data_len, 4.8])
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
plt.suptitle(title)
for index, fo_of_colnum in enumerate(meger_df_data.iloc[:, 7:-1]):
fo = meger_df_data[fo_of_colnum].values
plt.subplot(1, data_len, index + 1)
ob_sorted = np.sort(ob)
fo_sorted = np.sort(fo)
plt.plot(fo_sorted, ob_sorted)
if save_path is None:
plt.show()
else:
plt.savefig(save_path)
def contingency_table_multi_mode(ob, fo_list, grade=None, save_path='contingency_table.xls', sheet_name='sheet1'):
'''
:param ob_sta: 一个实况数据 类型 dataframe
:param fo_sta_list: 多模式预测数据 列表 类型list list中的类型是dataframe
每个dataframe 中的最后一列列名不能相同，表示时空数据的列为在前，列名相同
:param grade_list: 等级
:param save_path: 保存地址
:param sheet_name: xls 的sheet名
:return:
'''
fo_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_list)
ob_data = meger_df_data.iloc[:, -1]
ob_data = ob_data.values
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
if ':' in title:
title = title[:-13]
title = title.translate(str.maketrans(':', ':', string.punctuation))
save_path = title + '.xls'
for fo_of_colnum in meger_df_data.iloc[:, 7:-1]:
fo_of_data = meger_df_data[fo_of_colnum].values
yon.table.contingency_table(ob_data, fo_of_data, grade=grade, save_path=save_path,
sheet_name=fo_of_colnum)
def box_plot_muti_model(ob, fo_df_list, save_path=None, x_lable='observation', y_lable='forecast', title='box-plot'):
'''
box_plot 画一多模式数据的箱型图
---------------
:param observed:实况数据 df
:param forecast:预测数据 df列表
:param save_path: 保存数据的路径
:param x_lable: 横坐标的标签
:param y_lable:纵坐标标签
:param title: 图片名字
:return:
'''
fo_df_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_df_list)
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
ob = meger_df_data.iloc[:, -1]
meger_df_data.drop(meger_df_data.columns[-1], axis=1, inplace=True)
meger_df_data.insert(7, 'ob', ob)
labels = meger_df_data.columns[7:]
ob_and_fo_data = meger_df_data.iloc[:, 7:]
ob_and_fo_ndarray_T = ob_and_fo_data.values.T
ob_and_fo_tuple_T = tuple(ob_and_fo_ndarray_T)
plt.boxplot(ob_and_fo_tuple_T, labels=labels)
plt.title(title)
if save_path is None:
plt.show()
else:
plt.savefig(save_path)
def multi_mode_and_multi_classification_predictive_contingency_table(
ob, fo_list, grade_list=None, save_path=None):
'''
:param ob:一个实况数据 类型 dataframe
:param fo_list: 多模式预测数据 列表 类型list list中的类型是dataframe
每个dataframe 中的最后一列列名不能相同，表示时空数据的列为在前，列名相同
:param grade_list:等级 列表list
:param save_path: 保存地址
:return:
'''
fo_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_list)
meger_df_data.to_csv('aa.csv')
ob_data = meger_df_data.iloc[:, -1]
ob_data = ob_data.values
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
if ':' in title:
title = title[:-13]
title = title.translate(str.maketrans(':', ':', string.punctuation))
save_path = title + '.xls'
for fo_of_colnum in meger_df_data.iloc[:, 7:-1]:
fo_of_data = meger_df_data[fo_of_colnum].values
table.multi_category_contingency_table(ob_data,
fo_of_data,
grade_list=grade_list,
save_path=save_path)
def reliability_diagrams_muti_model(ob,
fo_list,
grade_list=None,
save_path=None,
diagona_color='r',
regression_line_color='g',
broken_line_color='b'):
'''
:param ob:
:param fo_list:
:param grade_list:
:param save_path:
:param diagona_color:
:param regression_line_color:
:param broken_line_color:
:return:
'''
fo_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_list)
ob = meger_df_data.iloc[:, -1].values
data_len = len(fo_list)
plt.figure(figsize=[6.4 * data_len, 4.8])
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
plt.suptitle(title)
for index, fo_of_colnum in enumerate(meger_df_data.iloc[:, 7:-1]):
fo = meger_df_data[fo_of_colnum].values
plt.subplot(1, data_len, index + 1)
if grade_list is None:
clevs = np.arange(0, 1.0, 10) # 如果没有给定概率等级，就设置默认等级
else:
clevs = grade_list
orfs = [0]
for i in range(1, len(clevs)):
index0 = np.where((fo > clevs[i - 1]) & (fo <= clevs[i]))
num = np.sum(ob[index0] == 1)
lenght = len(index0)
orf = num / lenght
orfs.append(orf)
orfs = np.array(orfs)
X = np.array(clevs)
X = X.reshape((len(X), -1))
model = LinearRegression().fit(X, orfs)
y = model.predict(X)
plt.plot(X, y, color=regression_line_color)
plt.plot(clevs, orfs, color=broken_line_color)
plt.scatter(clevs, orfs, color=broken_line_color)
plt.plot([0, 1], [0, 1], color=diagona_color)
if save_path is None:
plt.show()
else:
plt.savefig(save_path)
def scatter_regress_muti_model(ob, fo_df_list, save_path=None, scattercolor='r', scattersize=5,
x_label='fo', y_label='bo', fontsize=10, line_color='r'):
'''
scatter_regress_muti_model 多模式下画一张带有回归线的实况和预报数据的散点图
:param ob:一个实况数据 类型 dataframe
:param fo_list:多模式预测数据 列表 类型list list中的类型是dataframe
每个dataframe 中的最后一列列名不能相同，表示时空数据的列为在前，列名相同
:param save_path:保存地址
:param scattercolor:散点颜色
:param scattersize:散点的大小
:param x_label: 横坐标的名字
:param y_label: 纵坐标的名字
:param fontsize: 横纵坐标的名字字体大小
:param line_color:回归线的颜色
'''
fo_df_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_df_list)
ob = meger_df_data.iloc[:, -1].values
data_len = len(fo_df_list)
plt.figure(figsize=[6.4 * data_len, 4.8])
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
plt.suptitle(title)
for index, fo_of_colnum in enumerate(meger_df_data.iloc[:, 7:-1]):
fo = meger_df_data[fo_of_colnum].values
plt.subplot(1, data_len, index + 1)
plt.plot(ob, fo, 'o', markerfacecolor=scattercolor, markersize=scattersize)
# print(ob)
# print(fo)
ob_or_fo = np.hstack((ob, fo))
num_max = ob_or_fo.max()
num_min = ob_or_fo.min()
X = np.zeros((len(ob), 1))
X[:, 0] = ob
clf = LinearRegression().fit(X, fo)
ob_line = np.arange(0, np.max(ob), np.max(ob) / 30)
X = np.zeros((len(ob_line), 1))
X[:, 0] = ob_line
fo_rg = clf.predict(X)
plt.plot(ob_line, fo_rg, line_color)
plt.xlim(num_min - num_min / 5, num_max + num_max / 5)
plt.xlabel(x_label, size=fontsize)
plt.ylabel(y_label, size=fontsize)
plt.title(fo_of_colnum)
if save_path is None:
plt.show()
else:
plt.savefig(save_path)
def multi_mode_and_multi_classification_predictive_contingency_table(ob, fo_list, grade_list=None, save_path=None):
'''
:param ob:一个实况数据 类型 dataframe
:param fo_list: 多模式预测数据 列表 类型list list中的类型是dataframe
每个dataframe 中的最后一列列名不能相同，表示时空数据的列为在前，列名相同
:param grade_list:等级 列表list
:param save_path: 保存地址
:return:
'''
fo_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_list)
ob_data = meger_df_data.iloc[:, -1]
ob_data = ob_data.values
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
if ':' in title:
title = title[:-13]
title = title.translate(str.maketrans(':', ':', string.punctuation))
# print(title)
if save_path is None:
save_path = title + '.xlsx'
else:
save_path = save_path + '/' + title + '.xlsx'
pathlib.Path(save_path).touch()
writer = pd.ExcelWriter(save_path)
for fo_of_colnum in meger_df_data.iloc[:, 7:-1]:
fo_of_data = meger_df_data[fo_of_colnum].values
table.multi_category_contingency_table(ob_data, fo_of_data, grade_list=grade_list, is_append_sheet=True,
excel_writer=writer, sheet_name=fo_of_colnum, )
# multi_category_contingency_table(ob_data, fo_of_data, writer, fo_of_colnum, grade_list=grade_list)
writer.close()
def frequency_histogram_muti_model(ob, fo_list, clevs, x_lable='frequency', save_path=None,
y_lable='range', left_label='Obs', right_label='Pred',
left_color='r', right_color='b', legend_location="upper right", width=0.2):
'''
frequency_histogram_muti_model多模式下对比测试数据和实况数据的发生的频率
:param ob:一个实况数据 类型 dataframe
:param fo_list:多模式预测数据 列表 类型list list中的类型是dataframe
每个dataframe 中的最后一列列名不能相同，表示时空数据的列为在前，列名相同
:param clevs: 等级 列表
:param x_lable: 横坐标的名字
:param save_path: 保存地址
:param y_lable: 纵坐标的名字
:param left_label: 左标注名字
:param right_label: 右标注名字
:param left_color: 左柱状图的颜色
:param right_color: 右柱状图颜色
:param legend_location: 标注所处的地点
:param width: 宽度
:return:
'''
fo_list.append(ob)
meger_df_data = pisd.merge_on_id_and_obTime(fo_list)
ob = meger_df_data.iloc[:, -1].values
data_len = len(fo_list)-1
fig,axs = plt.subplots(1,data_len,figsize=(4*data_len, 4))
plt.subplots_adjust(left=0.05, bottom=0.1, right=0.95, top=0.88,
wspace=0.2, hspace=0.2)
colnums = ['level', 'id', 'time']
title = ''
for colnum in colnums:
the_duplicate_values = meger_df_data[colnum].unique()
if len(the_duplicate_values) == 1:
title = title + str(the_duplicate_values[0])
for index, fo_of_colnum in enumerate(meger_df_data.iloc[:, 7:-1]):
fo = meger_df_data[fo_of_colnum].values
#axe1 = plt.subplot(1, data_len, index + 1)
axe1 = axs[index]
p_ob = []
p_fo = []
xticklabels = []
for i in range(0, len(clevs) - 1):
index0 = np.where((ob >= clevs[i]) & (ob < clevs[i + 1]))
xticklabels.append(str(clevs[i]) + '-' + str(clevs[i + 1]))
p_ob.append(len(index0[0]) / len(ob))
index0 = np.where((fo >= clevs[i]) & (fo < clevs[i + 1]))
p_fo.append(len(index0[0]) / len(fo))
index0 = np.where(ob >= clevs[-1])
p_ob.append(len(index0[0]) / len(ob))
index0 = np.where(fo >= clevs[-1])
p_fo.append(len(index0[0]) / len(fo))
xticklabels.append('>=' + str(clevs[-1]))
x = np.arange(0, len(p_ob))
axe1.bar(x + 0.1, p_ob, width=width, facecolor=left_color, label=left_label)
axe1.bar(x - 0.1, p_fo, width=width, facecolor=right_color, label=right_label)
axe1.legend()
axe1.set_xlabel(x_lable, fontsize=10)
axe1.set_xticks(x)
axe1.set_xticklabels(xticklabels, fontsize=9)
axe1.set_ylabel(y_lable, fontsize=10)
axe1.yaxis.set_minor_locator(mpl.ticker.MultipleLocator(100))
axe1.set_title(fo_of_colnum)
plt.suptitle(title)
if save_path is None:
plt.show()
else:
plt.savefig(save_path)
