CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In

Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place.

| Download
Project: test
Views: 91872
Tweet
Share
Share
1
import numpy as np

2
import pylab as plt

3
from matplotlib.patches import Circle, Rectangle, Polygon, Arrow, FancyArrow

4
import book_plots

5


6
def create_predict_update_chart(box_bg = '#CCCCCC',

7
                arrow1 = '#88CCFF',

8
                arrow2 = '#88FF88'):

9
    plt.figure(figsize=(4,4), facecolor='w')

10
    ax = plt.axes((0, 0, 1, 1),

11
                  xticks=[], yticks=[], frameon=False)

12
    #ax.set_xlim(0, 10)

13
    #ax.set_ylim(0, 10)

14


15


16
    pc = Circle((4,5), 0.5, fc=box_bg)

17
    uc = Circle((6,5), 0.5, fc=box_bg)

18
    ax.add_patch (pc)

19
    ax.add_patch (uc)

20


21


22
    plt.text(4,5, "Predict\nStep",ha='center', va='center', fontsize=14)

23
    plt.text(6,5, "Update\nStep",ha='center', va='center', fontsize=14)

24


25
    #btm

26
    ax.annotate('',

27
                xy=(4.1, 4.5),  xycoords='data',

28
                xytext=(6, 4.5), textcoords='data',

29
                size=20,

30
                arrowprops=dict(arrowstyle="simple",

31
                                fc="0.6", ec="none",

32
                                patchB=pc,

33
                                patchA=uc,

34
                                connectionstyle="arc3,rad=-0.5"))

35
    #top

36
    ax.annotate('',

37
                xy=(6, 5.5),  xycoords='data',

38
                xytext=(4.1, 5.5), textcoords='data',

39
                size=20,

40
                arrowprops=dict(arrowstyle="simple",

41
                                fc="0.6", ec="none",

42
                                patchB=uc,

43
                                patchA=pc,

44
                                connectionstyle="arc3,rad=-0.5"))

45


46


47
    ax.annotate('Measurement ($\mathbf{z_k}$)',

48
                xy=(6.3, 5.4),  xycoords='data',

49
                xytext=(6,6), textcoords='data',

50
                size=18,

51
                arrowprops=dict(arrowstyle="simple",

52
                                fc="0.6", ec="none"))

53


54
    ax.annotate('',

55
                xy=(4.0, 3.5),  xycoords='data',

56
                xytext=(4.0,4.5), textcoords='data',

57
                size=18,

58
                arrowprops=dict(arrowstyle="simple",

59
                                fc="0.6", ec="none"))

60


61
    ax.annotate('Initial\nConditions ($\mathbf{x_0}$)',

62
                xy=(4.0, 5.5),  xycoords='data',

63
                xytext=(2.5,6.5), textcoords='data',

64
                size=18,

65
                arrowprops=dict(arrowstyle="simple",

66
                                fc="0.6", ec="none"))

67


68
    plt.text (4,3.4,'State Estimate ($\mathbf{\hat{x}_k}$)',

69
              ha='center', va='center', fontsize=18)

70
    plt.axis('equal')

71
    #plt.axis([0,8,0,8])

72
    plt.show()

73


74


75
def plot_estimate_chart_1():

76
    ax = plt.axes()

77
    ax.annotate('', xy=[1,159], xytext=[0,158],

78
                arrowprops=dict(arrowstyle='->', ec='r',shrinkA=6, lw=3,shrinkB=5))

79
    plt.scatter ([0], [158], c='b')

80
    plt.scatter ([1], [159], c='r')

81
    plt.xlabel('day')

82
    plt.ylabel('weight (lbs)')

83
    plt.show()

84


85


86
def plot_estimate_chart_2():

87
    ax = plt.axes()

88
    ax.annotate('', xy=[1,159], xytext=[0,158],

89
                arrowprops=dict(arrowstyle='->',

90
                                ec='r', lw=3, shrinkA=6, shrinkB=5))

91
    plt.scatter ([0], [158.0], c='k',s=128)

92
    plt.scatter ([1], [164.2], c='b',s=128)

93
    plt.scatter ([1], [159], c='r', s=128)

94
    plt.text (1.0, 158.8, "prediction ($x_t)$", ha='center',va='top',fontsize=18,color='red')

95
    plt.text (1.0, 164.4, "measurement ($z$)",ha='center',va='bottom',fontsize=18,color='blue')

96
    plt.text (0, 157.8, "estimate ($\hat{x}_{t-1}$)", ha='center', va='top',fontsize=18)

97
    plt.xlabel('day')

98
    plt.ylabel('weight (lbs)')    

99
    plt.show()

100


101
def plot_estimate_chart_3():

102
    ax = plt.axes()

103
    ax.annotate('', xy=[1,159], xytext=[0,158],

104
                arrowprops=dict(arrowstyle='->',

105
                                ec='r', lw=3, shrinkA=6, shrinkB=5))

106


107
    ax.annotate('', xy=[1,159], xytext=[1,164.2],

108
                arrowprops=dict(arrowstyle='-',

109
                                ec='k', lw=1, shrinkA=8, shrinkB=8))

110


111
    est_y = ((164.2-158)*.8 + 158)

112
    plt.scatter ([0,1], [158.0,est_y], c='k',s=128)

113
    plt.scatter ([1], [164.2], c='b',s=128)

114
    plt.scatter ([1], [159], c='r', s=128)

115
    plt.text (1.0, 158.8, "prediction ($x_t)$", ha='center',va='top',fontsize=18,color='red')

116
    plt.text (1.0, 164.4, "measurement ($z$)",ha='center',va='bottom',fontsize=18,color='blue')

117
    plt.text (0, 157.8, "estimate ($\hat{x}_{t-1}$)", ha='center', va='top',fontsize=18)

118
    plt.text (0.95, est_y, "new estimate ($\hat{x}_{t}$)", ha='right', va='center',fontsize=18)

119
    plt.xlabel('day')

120
    plt.ylabel('weight (lbs)')

121
    plt.show()

122


123
def plot_hypothesis():

124
    plt.errorbar([1, 2, 3], [170, 161, 169], 

125
                 xerr=0, yerr=10, fmt='bo', capthick=2, capsize=10)

126


127
    plt.plot([1, 3], [180, 160], color='g', ls='--')

128
    plt.plot([1, 3], [170, 170], color='g', ls='--')

129
    plt.plot([1, 3], [160, 175], color='g', ls='--')

130
    plt.plot([1, 2, 3], [180, 152, 179], color='g', ls='--')

131
    plt.xlim(0,4); plt.ylim(150, 185)

132
    plt.xlabel('day')

133
    plt.ylabel('lbs')

134
    plt.tight_layout()

135
    plt.show()

136
    

137
def plot_hypothesis2():

138
    plt.errorbar(range(1, 11), [169, 170, 169,171, 170, 171, 169, 170, 169, 170], 

139
                 xerr=0, yerr=6, fmt='bo', capthick=2, capsize=10)

140
    plt.plot([1, 10], [169, 170.5], color='g', ls='--')

141
    plt.xlim(0, 11); plt.ylim(150, 185)

142
    plt.xlabel('day')

143
    plt.ylabel('lbs')

144
    plt.show()

145
    

146
    

147
def plot_hypothesis3():   

148
    weights = [158.0, 164.2, 160.3, 159.9, 162.1, 164.6,

149
           169.6, 167.4, 166.4, 171.0, 171.2, 172.6]

150
    plt.errorbar(range(1, 13), weights,

151
                 xerr=0, yerr=6, fmt='o', capthick=2, capsize=10)

152


153
    plt.xlim(0, 13); plt.ylim(145, 185)

154
    plt.xlabel('day')

155
    plt.ylabel('weight (lbs)')

156
    plt.show()

157


158
    

159
def plot_hypothesis4():

160
    weights = [158.0, 164.2, 160.3, 159.9, 162.1, 164.6,

161
           169.6, 167.4, 166.4, 171.0, 171.2, 172.6]

162


163
    ave = np.sum(weights) / len(weights)

164
    plt.errorbar(range(1,13), weights, label='weights',

165
                 yerr=6, fmt='o', capthick=2, capsize=10)

166
    plt.plot([1, 12], [ave,ave], c='r', label='hypothesis')

167
    plt.xlim(0, 13); plt.ylim(145, 185)

168
    plt.xlabel('day')

169
    plt.ylabel('weight (lbs)')

170
    book_plots.show_legend()

171
    plt.show()

172


173
    

174
def plot_hypothesis5():   

175
    weights = [158.0, 164.2, 160.3, 159.9, 162.1, 164.6,

176
           169.6, 167.4, 166.4, 171.0, 171.2, 172.6]

177


178
    xs = range(1, len(weights)+1)

179
    line = np.poly1d(np.polyfit(xs, weights, 1))

180
    plt.errorbar(range(1, 13), weights, label='weights',

181
                 yerr=5, fmt='o', capthick=2, capsize=10)

182
    plt.plot (xs, line(xs), c='r', label='hypothesis')

183
    plt.xlim(0, 13); plt.ylim(145, 185)

184
    plt.xlabel('day')

185
    plt.ylabel('weight (lbs)')

186
    book_plots.show_legend()

187
    plt.show()

188


189
def plot_g_h_results(measurements, filtered_data, 

190
                     title='', z_label='Measurements', **kwargs):  

191
    book_plots.plot_filter(filtered_data, **kwargs)

192
    book_plots.plot_measurements(measurements, label=z_label)

193
    book_plots.show_legend()

194
    plt.title(title)

195
    plt.gca().set_xlim(left=0,right=len(measurements))

196
    

197
if __name__ == '__main__':

198
    create_predict_update_chart()

199