for k, v in enumerate(lin3.coef_[0]): print threeYrXcol[k], ": ", v # KNeighborsRegressor kn3 = KNReg(weights='uniform') #kn3.fit(df_3avg[threeYrXcol].values, df_3avg[threeYrycol].values) kn3.fit(X_train, y_train) print "Train: ", kn3.score(X_train, y_train) print "Test: ", kn3.score(X_test, y_test) # print kn3.score(df_3avg[threeYrXcol].values, df_3avg[threeYrycol].values) # RadiusNeighborsRegressor rn3 = RNReg(radius=7.0) #rn3.fit(df_3avg[threeYrXcol].values, df_3avg[threeYrycol].values) rn3.fit(X_train, y_train) print "Train: ", rn3.score(X_train, y_train) print "Test: ", rn3.score(X_test, y_test) print rn3.score(df_3avg[threeYrXcol].values, df_3avg[threeYrycol].values) # Test 2010/11/12 stats and 2013 projections against 2013 actuals y=2013 y3 = [y-1,y-2,y-3] tms_include = np.intersect1d(df[df.Year == y3[0]].Team.values, df[df.Year == y3[2]].Team.values) df2012 = pd.merge(df[(df.Year.isin(y3)) & (df.Team.isin(tms_include))].groupby('Team')[Xvar].mean(), df[(df.Year == y3[0]) & (df.Team.isin(tms_include))].groupby('Team')[Xvar].mean(), how='left',left_index=True, right_index=True, suffixes=['_3yr_avg','_yr3']) df2012['f2013'] = lin3.predict(df2012.values) df2012.sort('f_yr3', ascending=False, inplace=True) df2012['rnk_2012'] = range(1,df2012.shape[0]+1) df2012.sort('f2013', ascending=False, inplace=True) df2012['rnk_2013'] = range(1,df2012.shape[0]+1) #df2012.to_csv('f2013_projection_3yrs.csv', headers=True,index=True)