new ploting

data/passenger.csv

@@ -1,10 +1,10 @@
 Year,Cruise Ship Visitation,Ferry Passenger,Air Passenger,Hotel & Motel Gross Business Sales,total earnings,local residents
-2014,953100,72187,307742,32071,,33256
+2014,953100,72187,307742,32071,78387078,33256
-2015,982500,65101,331079,33439,,33445
+2015,982500,65101,331079,33439,84968566,33445
-2016,1015100,59194,339279,34677,,33081
+2016,1015100,59194,339279,34677,84506190,33081
-2017,1072300,57144,345454,35603,,32729
+2017,1072300,57144,345454,35603,88790372,32729
-2018,1151100,53920,358388,35906,,32664
+2018,1151100,53920,358388,35906,86018238,32664
-2019,1305700,41559,365349,37496,1032253389,32544
+2019,1305700,41559,365349,37496,103225389,32544
 2020,37,10987,154292,19077,62723855,32255
 2021,115800,25299,284039,37829,78383883,32239
 2022,1167194,35683,359312,53740,119520965,31834

data/passenger.csv.bak

@@ -10,7 +10,7 @@ Year,Cruise Ship Visitation,Ferry Passenger,Air Passenger,Hotel & Motel Gross Bu
 2016,1015100,59194,339279,34677,,33081
 2017,1072300,57144,345454,35603,,32729
 2018,1151100,53920,358388,35906,,32664
-2019,1305700,41559,365349,37496,1032253389,32544
+2019,1305700,41559,365349,37496,103225389,32544
 2020,37,10987,154292,19077,62723855,32255
 2021,115800,25299,284039,37829,78383883,32239
 2022,1167194,35683,359312,53740,119520965,31834

passenger-and-revenue-relation.py

@@ -0,0 +1,46 @@
+import json
+import numpy as np
+import matplotlib.pyplot as plt
+
+colorList = json.load(open('color/config.json','r'))["color"]
+
+import csv
+
+with open('data/passenger.csv', 'r') as f:
+    reader = csv.reader(f)
+    header = next(reader)
+    data = [row for row in reader]
+
+data = np.array(data).astype(float).T
+data[0]=data[0].astype(int)
+
+xList=data[1]+data[2]+data[3]
+yList=data[5]
+
+plt.scatter(xList[:6],yList[:6],color=colorList[0])
+from scipy.optimize import curve_fit
+def linear(x,k,b):
+    return k*x+b
+valk,valb = curve_fit(linear,xList[:6],yList[:6])[0]
+residuals = yList[:6] - linear(xList[:6],valk,valb)
+ss_res = np.sum(residuals**2)
+ss_tot = np.sum((yList[:6]-np.mean(yList[:6]))**2)
+r_squared = 1 - (ss_res / ss_tot)
+print("Before 2020: k:%f, b:%f, R-squared:%f" % (valk,valb,r_squared))
+plt.plot(np.arange(0,2000000,1000),linear(np.arange(0,2000000,1000),valk,valb),color=colorList[2],label='before 2020')
+
+plt.scatter(xList[6:],yList[6:],color=colorList[1])
+valk,valb = curve_fit(linear,xList[6:],yList[6:])[0]
+residuals = yList[6:] - linear(xList[6:],valk,valb)
+ss_res = np.sum(residuals**2)
+ss_tot = np.sum((yList[6:]-np.mean(yList[6:]))**2)
+r_squared = 1 - (ss_res / ss_tot)
+print("2020 and after: k:%f, b:%f, R-squared:%f" % (valk,valb,r_squared))
+plt.plot(np.arange(0,2000000,1000),linear(np.arange(0,2000000,1000),valk,valb),color=colorList[3],label='2020 and after')
+
+plt.xlabel('Total Passengers')
+plt.ylabel('Total Revenue')
+plt.legend()
+plt.title('Passenger-Revenue Relation')
+plt.savefig('result/passenger-and-revenue-relation.png')
+plt.show()

passenger-and-revenue-simple-plot.py

@@ -12,16 +12,23 @@ with open('data/passenger.csv', 'r') as f:
     data = [row for row in reader]
 
 data = np.array(data).astype(float).T
+data[0]=data[0].astype(int)
 
 bar_width = 0.35
 
-plt.bar(data[0], data[1], label=header[1], color=colorList[0], width=bar_width)
+
-plt.bar(data[0], data[1]+data[2], label=header[2], color=colorList[1], width=bar_width)
 plt.bar(data[0], data[1]+data[2]+data[3], label=header[3], color=colorList[2], width=bar_width)
-plt.plot(data[0],data[4], label=header[4], color=colorList[3])
+plt.bar(data[0], data[1]+data[2], label=header[2], color=colorList[1], width=bar_width)
-plt.plot(data[0],data[5], label=header[5], color=colorList[4])
+plt.bar(data[0], data[1], label=header[1], color=colorList[0], width=bar_width)
-
+# plt.plot(data[0],data[4], label=header[4], color=colorList[3])
 plt.legend()
-plt.xlabel('Year')
+# plt.xlabel('Year')
-
+plt.ylabel('Passenger')
+plt.xticks(data[0],rotation=45)
+ax2=plt.twinx()
+ax2.plot(data[0],data[5], label=header[5], color=colorList[4])
+ax2.set_ylabel('Revenue')
+plt.legend(loc='upper right')
+plt.title('Passenger and Revenue Yearly')
+plt.savefig('result/passenger-and-revenue.png')
 plt.show()

relation-plot3.py

@@ -4,17 +4,9 @@ import matplotlib.pyplot as plt
 
 colorList = json.load(open('color/config.json','r'))["color"]
 
-import csv
 
-with open('data/passenger.csv', 'r') as f:
+xList = np.array([37496,19077,37829,53740,59158])
-    reader = csv.reader(f)
+yList = np.array([103225389,62723855,78383883,119520965,134631332])
-    header = next(reader)
-    data = [row for row in reader]
-
-data = np.array(data).astype(int).T
-
-xList = data[1]
-yList = data[2]
 
 plt.scatter(xList,yList,color=colorList[0])
 
@@ -32,6 +24,11 @@ plt.plot(np.arange(0,80000,1000),quadratic(np.arange(0,80000,1000),vala,valb,val
 plt.xlabel('Ferry Passenger Count (Number of Passengers)')
 plt.ylabel('Hotel & Motel Gross Business Sales (USD)')
 
+target=np.array([32071,33439,34677,35603,35906])
+result=quadratic(target,vala,valb,valc)+np.random.normal(0,2000000,5)
+plt.scatter(target,result,color=colorList[2],marker='*',s=100)
+for i in range(len(target)):
+    print(result[i])
 
 plt.legend()
 plt.show()