base_dir = '/Users/james/Data_Incubator/loan-picker'
#base_dir = os.path.dirname(os.path.realpath(__file__))
data_dir = os.path.join(base_dir,'static/data/')
fig_dir = os.path.join(base_dir,'static/images/')
movie_dir = os.path.join(base_dir,'static/movies/')
data_name = 'all_loans_proc'
LD = pd.read_csv(data_dir + data_name, parse_dates=['issue_d'])
fips_data = LCL.load_location_data(data_dir, group_by='fips')
zip3_data = LCL.load_location_data(data_dir, group_by='zip3')
fips_to_zip = LCL.make_fips_to_zip_dict(data_dir, group_by='zip')
#%% make a k-tree for doing nearest neighbor imputation of missing data
base_map = LCL.load_base_map(fig_dir + 'USA_Counties_text.svg', ax_xml=True)
(county_paths,state_paths) = LCL.get_map_paths(base_map,fips_to_zip)
title_path = base_map.findAll('text')[0]
map_coords = LCH.extract_fips_coords(county_paths)
ktree = KDTree(map_coords.values) #make nearest neighbor tree
#%% make sequence of decision trees and build a movie
X = LD[['longitude','latitude']]
y = LD['ROI'] #plot average return by area, not portfolio return
max_levels = 16
min_samples_leaf = 50
pred_arr = np.zeros((len(fips_data),max_levels))
for n in xrange(max_levels):
clf = tree.DecisionTreeRegressor(max_depth=n+1, min_samples_leaf=min_samples_leaf, random_state=0)
clf.fit(X, y)
def reset_map():
print('resetting map')
app.base_map = LCL.load_base_map(fig_dir + map_name)
(app.county_paths,app.state_paths) = LCL.get_map_paths(app.base_map,fips_to_zip)
return redirect('/loan_mapping')
def reset_map():
print('resetting map')
app.base_map = LCL.load_base_map(fig_dir + map_name)
(app.county_paths,
app.state_paths) = LCL.get_map_paths(app.base_map, fips_to_zip)
return redirect('/loan_mapping')
#load lookup tables for converting zips and states to county FIPS codes for plotting
fips_to_zip = dill.load(open(data_dir + 'fips_to_zip.p', "rb" ) )
state_fips_dict = dill.load(open(data_dir + 'state_fips_dict.p',"rb"))
#get lat/long coordinates for each 3-digit zip
zip3_loc_path = os.path.join(data_dir,'zip3_loc_data.p')
with open(zip3_loc_path,'rb') as in_strm:
zip3_loc_data = dill.load(in_strm)
# precompute additional columns for convenience when plotting
LD['short_purpose'] = LD['purpose'].map(purpose_map)
LD['issue_year'] = LD['issue_d'].dt.year
# load base map and get state and county paths
app.base_map = LCL.load_base_map(fig_dir + map_name)
(app.county_paths,app.state_paths) = LCL.get_map_paths(app.base_map,fips_to_zip)
predictor = namedtuple('predictor', ['col_name', 'full_name', 'norm_type'])
model_data = LCP.load_pickled_models()
sim_lookup = LCP.get_validation_data()
#%%
use_grades = ['A','B','C','D','E','F']
load_time = time.time()
print('Grabbing loan data at {}'.format(load_time))
predictions = LCP.get_LC_loans(auth_keys['LC_auth_key'], model_data,
zip3_loc_data, use_grades)
#%%
@app.route('/') #redirect to index page
#load lookup tables for converting zips and states to county FIPS codes for plotting
fips_to_zip = dill.load(open(data_dir + 'fips_to_zip.p', "rb"))
state_fips_dict = dill.load(open(data_dir + 'state_fips_dict.p', "rb"))
#get lat/long coordinates for each 3-digit zip
zip3_loc_path = os.path.join(data_dir, 'zip3_loc_data.p')
with open(zip3_loc_path, 'rb') as in_strm:
zip3_loc_data = dill.load(in_strm)
# precompute additional columns for convenience when plotting
LD['short_purpose'] = LD['purpose'].map(purpose_map)
LD['issue_year'] = LD['issue_d'].dt.year
# load base map and get state and county paths
app.base_map = LCL.load_base_map(fig_dir + map_name)
(app.county_paths,
app.state_paths) = LCL.get_map_paths(app.base_map, fips_to_zip)
predictor = namedtuple('predictor', ['col_name', 'full_name', 'norm_type'])
model_data = LCP.load_pickled_models()
sim_lookup = LCP.get_validation_data()
#%%
use_grades = ['A', 'B', 'C', 'D', 'E', 'F']
load_time = time.time()
print('Grabbing loan data at {}'.format(load_time))
predictions = LCP.get_LC_loans(auth_keys['LC_auth_key'], model_data,
zip3_loc_data, use_grades)
