-
Notifications
You must be signed in to change notification settings - Fork 1
/
statistics_2.py
73 lines (52 loc) · 1.78 KB
/
statistics_2.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
import pandas as pd
import matplotlib as m
m.use('TkAgg')
import matplotlib.pyplot as plt
#import numpy as np
import quandl
#from matplotlib import style
#style.use('ggplot')
import pickle
api_key = ''
#df = quandl.get('FMAC/HPI_AK', authtoken = api_key)
#print df.head()
def state_list():
fiddy_states = pd.read_html('https://simple.wikipedia.org/wiki/List_of_U.S._states')
return fiddy_states[0][0][1:]
def grab_initial_state_data():
states = state_list()
main_df = pd.DataFrame()
for abbv in states:
query = "FMAC/HPI_"+str(abbv)
df = quandl.get(query, authtoken=api_key)
df = df.rename(columns = {'Value':abbv})
# df = df.pct_change()
df[abbv] = (df[abbv] -df[abbv][0] / df[abbv][0] * 100.0)
# print df.head()
# print(query)
if main_df.empty:
main_df = df
else:
# main_df = pd.merge(main_df, df, right_index=True, left_index=True)
# main_df = main_df.join(df, lsuffix='_left', rsuffix='_right')
main_df = main_df.join(df)
pickle_out = open('fiddy_states3.pickle','wb')
pickle.dump(main_df, pickle_out)
pickle_out.close()
print df.head()
def HPI_Benchmark():
df = quandl.get("FMAC/HPI_USA", authtoken = api_key)
df["Value"] = (df["Value"] -df["Value"][0] / df["Value"][0] * 100.0)
return df
#grab_initial_state_data()
fig = plt.figure()
ax1 = plt.subplot2grid((2,1),(0,0))
ax2 = plt.subplot2grid((2,1),(1,0), sharex = ax1)
HPI_data = pd.read_pickle('fiddy_states3.pickle')
TX_AK_12corr = pd.rolling_corr(HPI_data['TX'], HPI_data['AK'], 12)
HPI_data['TX'].plot(ax = ax1, label= 'TX HPI')
HPI_data['AK'].plot(ax = ax1, label= 'AK HPI')
ax1.legend(loc = 4)
TX_AK_12corr.plot(ax = ax2, label = 'TX_AK_12corr')
plt.legend(loc = 4)
plt.show()