(This article was first published on

**Yet Another Blog in Statistical Computing » S+/R**, and kindly contributed to R-bloggers)In [1]: # LOAD PACKAGES In [2]: import pandas as pd In [3]: import numpy as np In [4]: from sklearn import preprocessing as pp In [5]: from sklearn import cross_validation as cv In [6]: from neupy.algorithms import GRNN as grnn In [7]: from neupy.functions import mse In [8]: # DATA PROCESSING In [9]: df = pd.read_table("csdata.txt") In [10]: y = df.ix[:, 0] In [11]: y.describe() Out[11]: count 4421.000000 mean 0.090832 std 0.193872 min 0.000000 25% 0.000000 50% 0.000000 75% 0.011689 max 0.998372 Name: LEV_LT3, dtype: float64 In [12]: x = df.ix[:, 1:df.shape[1]] In [13]: st_x = pp.scale(x) In [14]: st_x.mean(axis = 0) Out[14]: array([ 1.88343648e-17, 5.76080438e-17, -1.76540780e-16, -7.71455583e-17, -3.80705294e-17, 3.79409490e-15, 4.99487355e-17, -2.97100804e-15, 3.93261537e-15, -8.70310886e-16, -1.30728071e-15]) In [15]: st_x.std(axis = 0) Out[15]: array([ 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]) In [16]: x_train, x_test, y_train, y_test = cv.train_test_split(st_x, y, train_size = 0.7, random_state = 2015) In [17]: # TRAIN THE NEURAL NETWORK In [18]: def try_std(x): ....: nn = grnn(std = x, verbose = False) ....: nn.train(x_train, y_train) ....: y_pred = nn.predict(x_test) ....: print mse(y_pred, y_test) ....: In [19]: # TEST A LIST OF VALUES FOR THE TUNING PARAMETER In [20]: for x in np.linspace(0.5, 1.5, 11): ....: print x ....: try_std(x) ....: 0.5 0.034597892756 0.6 0.0331189699098 0.7 0.0323384657283 0.8 0.0319580849146 0.9 0.0318001764256 1.0 0.031751821704 1.1 0.031766356369 1.2 0.03183082142 1.3 0.0319348198865 1.4 0.0320623872248 1.5 0.03219800235

To

**leave a comment**for the author, please follow the link and comment on their blog:**Yet Another Blog in Statistical Computing » S+/R**.R-bloggers.com offers

**daily e-mail updates**about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...