def prediction():
with tf.variable_scope("sec_lstm", reuse=tf.AUTO_REUSE):
pred, _ = lstm(1) #预测时只输入[1,time_step,input_size]的测试数据
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
saver.restore(sess, 'model_save1\\modle.ckpt') #参数恢复
# I run the code in windows 10,so use 'model_save1\\modle.ckpt'
# if you run it in Linux,please use 'model_save1/modle.ckpt'
# 取训练集最后一行为测试样本。shape=[1,time_step,input_size]
prev_seq = train_x[-1]
predict = []
# 得到之后100个预测结果
for i in range(100):
next_seq = sess.run(pred, feed_dict={X: [prev_seq]})
predict.append(next_seq[-1])
# 每次得到最后一个时间步的预测结果，与之前的数据加在一起，形成新的测试样本
prev_seq = np.vstack((prev_seq[1:], next_seq[-1]))
# 以折线图表示结果
plt.figure()
plt.plot(list(range(len(normalize_data))), normalize_data, color='b')
plt.plot(list(
range(len(normalize_data),
len(normalize_data) + len(predict))),
predict,
color='r')
plt.show()
def prediction(time_step=20):
X = tf.placeholder(tf.float32, shape=[None, time_step, input_size])
mean, std, test_x, test_y = get_test_data(time_step)
with tf.variable_scope("sec_lstm", reuse=tf.AUTO_REUSE):
pred, _ = lstm(X)
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
# 参数恢复
module_file = tf.train.latest_checkpoint('model_save2')
saver.restore(sess, module_file)
test_predict = []
for step in range(len(test_x) - 1):
prob = sess.run(pred, feed_dict={X: [test_x[step]], keep_prob: 1})
predict = prob.reshape((-1))
test_predict.extend(predict)
test_y = np.array(test_y) * std[7] + mean[7]
test_predict = np.array(test_predict) * std[7] + mean[7]
acc = np.average(
np.abs(test_predict - test_y[:len(test_predict)]) /
test_y[:len(test_predict)]) # 偏差程度
print("The accuracy of this predict:", acc)
# 以折线图表示结果
plt.figure()
plt.plot(
list(range(len(test_predict))),
test_predict,
color='b',
)
plt.plot(list(range(len(test_y))), test_y, color='r')
plt.show()
def drowPicture(History):
pyplot.plot(History.history['loss'])
pyplot.plot(History.history['val_loss'])
pyplot.plot(History.history['acc'])
pyplot.plot(History.history['val_acc'])
pyplot.title('model train vs validation loss')
pyplot.ylabel('loss')
pyplot.xlabel('epoch')
pyplot.legend(['train', 'validation'], loc='upper right')
pyplot.show()
def main_test():
print("主要测试")
import numpy as np
s = np.random.uniform(1, 2, 1000)
# print(np.all(s >= 2))
# print(s)
# exit()
import Example_matplotlib.pyplot as plt
count, bins, ignored = plt.hist(s, 15, density=True)
plt.plot(bins, np.ones_like(bins), linewidth=2, color='r')
plt.show()
def plot_forecasts(series, forecasts, n_test):
# plot the entire dataset in blue
pyplot.plot(series.values)
# plot the forecasts in red
for i in range(len(forecasts)):
off_s = len(series) - n_test + i - 1
off_e = off_s + len(forecasts[i]) + 1
xaxis = [x for x in range(off_s, off_e)]
yaxis = [series.values[off_s]] + forecasts[i]
pyplot.plot(xaxis, yaxis, color='red')
# show the plot
pyplot.show()
def plot_forecasts(series, forecasts, n_test):
# 蓝线画出真实数据
pyplot.plot(series.values)
# 红线画出预测值
for i in range(len(forecasts)):
off_s = len(series) - n_test + i - 1
off_e = off_s + len(forecasts[i]) + 1
# 赋值x轴坐标
xaxis = [x for x in range(off_s, off_e)]
# 赋值y轴坐标
yaxis = [series.values[off_s]] + forecasts[i]
pyplot.plot(xaxis, yaxis, color='red')
pyplot.show()
def plot_forcasts(series, forcasts, n_test):
# 原始数据
pyplot.plot(series.values)
# 预测数据
for i in range(len(forcasts)):
off_s = len(series) - n_test + i - 1
off_e = off_s + len(forcasts[i]) + 1
xaxis = [x for x in range(off_s, off_e)]
yaxis = [series.values[off_s]] + forcasts[i]
print('xaxis')
print(xaxis)
print('yaxis')
print(yaxis)
print('series.values[off_s]')
print(series.values[off_s])
pyplot.plot(xaxis, yaxis, color='red')
pyplot.show()
def plot_results(xlog, ulog):
t = [0.25 * x for x in range(xlog.shape[1])]
plt.figure()
plt.subplot(311)
plt.plot(t, xlog[3, :], label="altitude", color="b")
plt.ylabel('altitude')
plt.subplot(312)
plt.plot(t, xlog[1, :], label="pitch angle", color="r")
plt.ylabel('pitch angle')
plt.subplot(313)
plt.plot(t, ulog[0, :], label="elevator angle", color="g")
plt.ylabel('elevator angle')
plt.show()
# @Time : 2019/9/27 0027 13:57 # @Author :zhu # @File : pro_view.py # @task description : import tensorflow as tf import numpy as np import Example_matplotlib.pyplot as plt plt.rcParams["figure.figsize"] = (14, 8) # 生成随机数 n_observations = 100 xs = np.linspace(-3, 3, n_observations) ys = np.sin(xs) + np.random.uniform(-0.5, 0.5, n_observations) plt.scatter(xs, ys) plt.show() # 定义容器,放入X和Y X = tf.placeholder(tf.float32, name="X") Y = tf.placeholder(tf.float32, name="Y") # 定义权重和偏置,对应与一次线性函数y = wx + b w = tf.Variable(tf.random_normal([1]), name="weight") b = tf.Variable(tf.random_normal([1]), name="bias") # 进行计算预测Y_Pre Y_Pre = tf.add(tf.multiply(X, w), b) # 计算损失的函数值,就是平方差 loss = tf.square(Y - Y_Pre, name="loss") # 初始化 learning_rate = 0.01 optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss) # 给出迭代次数,并且加入 Session执行 n_samples = xs.shape[0]
# 使用构造的网络模型进行预测训练
lstm_model.predict(train_reshaped, batch_size=1)
#print(lstm_model.predict(train_reshaped, batch_size=1))
# 遍历测试数据，对数据进行单步预测
predictions = list()
for i in range(len(test_scaled)):
# 将(12,2)的2D训练集test_scaled拆分成X,y；
# 其中X是第i行的0到-1列，形状是(1,)的包含一个元素的一维数组；y是第i行，倒数第1列，是一个数值；
X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
# 将训练好的模型lstm_model，X变量，传入预测函数，定义步长为1，
yhat = forecast_lstm(lstm_model, 1, X)
print(yhat.shape)
# 对预测出的y值逆缩放
yhat = invert_scale(scaler, X, yhat)
# 对预测出的y值逆差分转换
#yhat = inverse_difference(raw_values, yhat, len(test_scaled)+1-i)
# 存储预测的y值
predictions.append(yhat)
# 获取真实的y值
expected = raw_values[len(train) + i + 1]
#
print('Month=%d, Predicted=%f, Expected=%f' % (i + 1, yhat, expected))
# 求真实值和预测值之间的标准差
rmse = sqrt(mean_squared_error(raw_values[-testNum:], predictions))
print('Test RMSE: %.3f' % rmse)
# 作图展示
pyplot.plot(raw_values[-testNum:])
pyplot.plot(predictions)
pyplot.show()
def pic_map():
import numpy as np
import pandas as pd
import Example_matplotlib.pyplot as plt
from mpl_toolkits.basemap import Basemap
from Example_matplotlib.patches import Polygon
from Example_matplotlib.colors import rgb2hex
from Example_matplotlib.collections import PatchCollection
from Example_matplotlib import pylab
plt.rcParams['font.sans-serif'] = ['KaiTi'] # 指定默认字体
plt.rcParams['axes.unicode_minus'] = False
plt.figure(figsize=(20, 10)) # 长和宽
# m= Basemap(llcrnrlon=73, llcrnrlat=18, urcrnrlon=135, urcrnrlat=55) #指定中国的经纬度
m = Basemap(llcrnrlon=77,
llcrnrlat=14,
urcrnrlon=140,
urcrnrlat=51,
projection='lcc',
lat_1=33,
lat_2=45,
lon_0=100) # ‘lcc'将投影方式设置为兰伯特投影
# projection='ortho' # 投影方式设置为正投影——类似地球仪
CHN = r'C:\Users\Administrator\Desktop\MyProject\Test_module\Test_matplotlib\data_base'
m.readshapefile(CHN + r'\gadm36_CHN_shp\gadm36_CHN_1',
'states',
drawbounds=True) # 加省界
# 读取数据
df = pd.read_csv('./data_base/data/chnpop.csv')
df['省名'] = df.省名.str[:2]
df.set_index('省名', inplace=True)
# 把每个省的数据映射到colormap上
statenames = []
colors = {}
patches = []
cmap = plt.cm.YlOrRd # 国旗色红黄色调
vmax = 10**8
vmin = 3 * 10**6
# 处理地图包里的省名
for shapedict in m.states_info:
statename = shapedict['NL_NAME_1']
p = statename.split('|')
if len(p) > 1:
s = p[1]
else:
s = p[0]
s = s[:2]
if s == '黑龍':
s = '黑龙'
statenames.append(s)
pop = df['人口数'][s]
colors[s] = cmap(np.sqrt(
(pop - vmin) / (vmax - vmin)))[:3] # 根据归一化后的人口数映射颜色
# exit()
ax = plt.gca()
for nshape, seg in enumerate(m.states):
color = rgb2hex(colors[statenames[nshape]])
poly = Polygon(seg, facecolor=color, edgecolor=color)
patches.append(poly)
ax.add_patch(poly)
# 图片绘制加上台湾（台湾不可或缺）
m.readshapefile(CHN + '\gadm36_TWN_shp\gadm36_TWN_1',
'taiwan',
drawbounds=True)
for nshape, seg in enumerate(m.taiwan):
poly = Polygon(seg, facecolor='w')
patches.append(poly)
ax.add_patch(poly)
# 添加colorbar 渐变色legend
colors1 = [i[1] for i in colors.values()]
colorVotes = plt.cm.YlOrRd
p = PatchCollection(patches, cmap=colorVotes)
p.set_array(np.array(colors1))
pylab.colorbar(p)
#4266831.094478747, 1662846.3046657
lon = 4097273.638675578
lat = 4008859.232616643
x, y = m(lon, lat)
plt.text(x,
y,
'国都',
fontsize=120,
fontweight='bold',
ha='left',
va='bottom',
color='k')
m.scatter(x, y, s=200, marker='*', facecolors='r', edgecolors='B') # 绘制首都
plt.title(u'祝鑫泉画的World Map ', fontsize=24)
plt.savefig("./data_base/result/Chinese_Map1.png", dpi=100) # 指定分辨率
plt.show()
