In [1]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model


    

In [2]:

    

statelist=["AK","AL","AR","AZ","CA","CO","CT","DC","DE","FL","GA","HI","IA","ID","IL","IN","KS","KY","LA","MA","MD","ME","MI","MN","MO","MS","MT","NC","ND","NE","NH","NJ","NM","NV","NY","OH","OK","OR","PA","RI","SC","SD","TN","TX","US","UT","VA","VT","WA","WI","WV","WY"]
print(len(statelist))


    

    




52

In [10]:

    

fn_ext = '.csv'
filename = []

for state in statelist:
    fn = "".join((state, fn_ext))
    filename.append(fn)
    df = pd.read_csv(fn)
    print(df.shape[0])


    

    




57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57
57

In [11]:

    

#reshape the input for each three years
OP_array = df["Inflation Adjusted Price"].values
OP = OP_array.reshape(-1,1)

result = []
for i in range(len(OP_array) - 2):
    result.append([OP_array[i], OP_array[i+1], OP_array[i+2]])
OP_newx = np.array(result)
OP_newy = OP_array[3:].reshape(-1,1)

OP_newx_train = OP_newx[:-6]
OP_newy_train = OP_newy[:-5]
OP_newx_test = OP_newx[-6:]
OP_newy_test = OP_newy[-5:]

#Lasso regression
regr = linear_model.Lasso()
regr.fit(OP_newx_train, OP_newy_train)

OP_lassoy_train = regr.predict(OP_newx_train)
OP_lassoy_test = regr.predict(OP_newx_test)

year_all = np.append(df.Year.values, [2017, 2018, 2019])
y_lasso = np.append(OP_lassoy_train, OP_lassoy_test)

OP_17_y = y_lasso[-1]
print(OP_17_y)
OP_18_x = np.append(OP_array[-2:], OP_17_y)
print(OP_18_x)
OP_18_y = regr.predict(OP_18_x)
print(OP_18_y)

OP_18 = OP_18_y.item(0)
OP_19_x = np.append(OP_18_x[-2:], OP_18)
print(OP_19_x)
OP_19_y = regr.predict(OP_19_x)
print(OP_19_y)
OP_19 = OP_19_y.item(0)

y_lasso_all = np.append(y_lasso, [OP_18, OP_19])

plt.figure()
plt.scatter(df.Year.reshape(-1,1), df["Inflation Adjusted Price"])
plt.scatter(year_all[-2:].reshape(-1,1), y_lasso_all[-2:], color='red')
plt.plot(year_all[3:].reshape(-1,1), y_lasso_all)
plt.show()


    

    




---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/Users/kejiawu/anaconda/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   2133             try:
-> 2134                 return self._engine.get_loc(key)
   2135             except KeyError:

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)()

KeyError: 'Inflation Adjusted Price'

During handling of the above exception, another exception occurred:

KeyError                                  Traceback (most recent call last)
<ipython-input-11-2140103ac4b3> in <module>()
      1 #reshape the input for each three years
----> 2 OP_array = df["Inflation Adjusted Price"].values
      3 OP = OP_array.reshape(-1,1)
      4 
      5 result = []

/Users/kejiawu/anaconda/lib/python3.5/site-packages/pandas/core/frame.py in __getitem__(self, key)
   2057             return self._getitem_multilevel(key)
   2058         else:
-> 2059             return self._getitem_column(key)
   2060 
   2061     def _getitem_column(self, key):

/Users/kejiawu/anaconda/lib/python3.5/site-packages/pandas/core/frame.py in _getitem_column(self, key)
   2064         # get column
   2065         if self.columns.is_unique:
-> 2066             return self._get_item_cache(key)
   2067 
   2068         # duplicate columns & possible reduce dimensionality

/Users/kejiawu/anaconda/lib/python3.5/site-packages/pandas/core/generic.py in _get_item_cache(self, item)
   1384         res = cache.get(item)
   1385         if res is None:
-> 1386             values = self._data.get(item)
   1387             res = self._box_item_values(item, values)
   1388             cache[item] = res

/Users/kejiawu/anaconda/lib/python3.5/site-packages/pandas/core/internals.py in get(self, item, fastpath)
   3541 
   3542             if not isnull(item):
-> 3543                 loc = self.items.get_loc(item)
   3544             else:
   3545                 indexer = np.arange(len(self.items))[isnull(self.items)]

/Users/kejiawu/anaconda/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   2134                 return self._engine.get_loc(key)
   2135             except KeyError:
-> 2136                 return self._engine.get_loc(self._maybe_cast_indexer(key))
   2137 
   2138         indexer = self.get_indexer([key], method=method, tolerance=tolerance)

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)()

KeyError: 'Inflation Adjusted Price'

In [ ]: