-
Notifications
You must be signed in to change notification settings - Fork 0
/
MobilityVsIR.py
156 lines (139 loc) · 5.45 KB
/
MobilityVsIR.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
import csv
from matplotlib import pyplot as plt
path = "csv/Unemployment.csv"
incomes = {}
retail_and_recreation = {}
grocery_and_pharmacy = {}
parks = {}
transit_stations = {}
workplaces = {}
residential = {}
avg = {}
num_points = {}
ir = {}
with open(path, "r") as csv_file:
csv_reader = csv.reader(csv_file, delimiter=",")
for line in csv_reader:
if line[87] != '' and len(line[87]) < 10:
incomes[line[0]] = float(line[87])
path = "csv/Doubling_time_by_fips.csv"
with open(path, "r") as csv_file:
csv_reader = csv.reader(csv_file, delimiter=",")
for line in csv_reader:
if line[0] != "FIPS":
ir[line[0]] = float(line[2])
path = "csv/Mobility_by_fips.csv"
with open(path, "r") as csv_file:
csv_reader = csv.reader(csv_file, delimiter=",")
for line in csv_reader:
if line[0] != "FIPS":
retail_and_recreation[line[0]] = float(line[1])
grocery_and_pharmacy[line[0]] = float(line[2])
parks[line[0]] = float(line[3])
transit_stations[line[0]] = float(line[4])
workplaces[line[0]] = float(line[5])
residential[line[0]] = float(line[6])
avg[line[0]] = float(line[7])
num_points[line[0]] = float(line[8])
retail_and_recreation_by_fips = []
grocery_and_pharmacy_by_fips = []
parks_by_fips = []
transit_stations_by_fips = []
workplaces_by_fips = []
residential_by_fips = []
avg_by_fips = []
incomes_by_fips = []
ir_by_fips = []
for fips in incomes:
if fips in retail_and_recreation and fips in ir and num_points[fips] > 10:
retail_and_recreation_by_fips.append(retail_and_recreation[fips])
grocery_and_pharmacy_by_fips.append(grocery_and_pharmacy[fips])
parks_by_fips.append(parks[fips])
transit_stations_by_fips.append(transit_stations[fips])
workplaces_by_fips.append(workplaces[fips])
residential_by_fips.append(residential[fips])
avg_by_fips.append(avg[fips])
incomes_by_fips.append(incomes[fips])
ir_by_fips.append(ir[fips])
retail_and_recreation_np = np.array([[x] for x in retail_and_recreation_by_fips])
grocery_and_pharmacy_by_fips_np = np.array([[x] for x in grocery_and_pharmacy_by_fips])
parks_by_fips_np = np.array([[x] for x in parks_by_fips])
transit_stations_by_fips_np = np.array([[x] for x in transit_stations_by_fips])
workplaces_by_fips_np = np.array([[x] for x in workplaces_by_fips])
residential_by_fips_np = np.array([[x] for x in residential_by_fips])
avg_by_fips_np = np.array([[x] for x in avg_by_fips])
incomes_by_fips_np = np.array([[x] for x in incomes_by_fips])
ir_by_fips_np = np.array([[x] for x in ir_by_fips])
temp1 = np.append(retail_and_recreation_np, grocery_and_pharmacy_by_fips_np, 1)
temp2 = np.append(temp1, parks_by_fips_np, 1)
temp3 = np.append(temp2, transit_stations_by_fips_np, 1)
temp4 = np.append(temp3, workplaces_by_fips_np, 1)
temp5 = np.append(temp4, residential_by_fips_np, 1)
temp6 = np.append(temp5, avg_by_fips_np, 1)
temp7 = np.append(temp6, incomes_by_fips_np, 1)
all_data = np.append(temp7, ir_by_fips_np, 1)
df = pd.DataFrame(all_data, columns=['retail and recreation', 'grocery and pharmacy',
'parks', 'transit stations', 'workplaces', 'residential',
'avg', 'incomes', 'ir'])
X = df[['retail and recreation', 'grocery and pharmacy', 'parks', 'transit stations', 'workplaces', 'residential']]
y = df['ir']
X1 = df[['retail and recreation']]
X2 = df[['grocery and pharmacy']]
X3 = df[['parks']]
X4 = df[['transit stations']]
X5 = df[['workplaces']]
X6 = df[['residential']]
model = LinearRegression()
model.fit(X,y)
print("Multiple linear regression (retail & recreation, grocery & pharmacy vs doubling time):")
r_sq = model.score(X, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()
print("Linear regression (retail and recreation vs doubling time):")
model.fit(X1,y)
r_sq = model.score(X1, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()
print("Linear regression (grocery and pharmacy vs doubling time):")
model.fit(X2,y)
r_sq = model.score(X2, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()
print("Linear regression (parks vs doubling time):")
model.fit(X3,y)
r_sq = model.score(X3, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()
print("Linear regression (transit stations vs doubling time):")
model.fit(X4,y)
r_sq = model.score(X4, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()
print("Linear regression (workplaces vs doubling time):")
model.fit(X5,y)
r_sq = model.score(X5, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()
print("Linear regression (residential vs doubling time):")
model.fit(X6,y)
r_sq = model.score(X6, y)
print('coefficient of determination:', r_sq)
print('intercept:', model.intercept_)
print('slope:', model.coef_)
print()