I am a newbie in neural network. I have to make a model predicting total number of typhoons for each months, using 22 indices. I have total numbers of typhoons and 22 indices for certain period from 1979 to 2008. I know I need to use RNN for making this model but have no idea about spliting train and test set of my dataset and hard to plot my results.
This is how my dataset looks.
SF 10.7 SOI N12 N3 N34 N4 BEST lv TNA TSA WHWP ... PWR TPSE ATSE AMOL AMM NTA CAR QBO GIAM counts
Unnamed: 0
1979 1803.0 1.1 0.16 -0.15 -0.29 -0.24 -0.08 0.42 0.10 -0.81 ... -0.200 0.517 0.514 -0.051 1.96 0.11 -0.20 -19.60 0.68 2
1980 1932.0 -0.0 -0.36 0.08 0.21 0.16 0.64 0.47 -0.08 1.21 ... -0.163 0.781 0.645 0.100 3.64 0.07 0.10 7.33 0.45 3
1981 1569.0 2.0 -0.63 -0.43 -0.46 -0.59 -0.47 0.18 -0.22 -0.80 ... -0.041 -0.190 0.220 -0.066 2.19 -0.07 -0.08 -3.49 0.20 0
1982 1719.0 -1.7 0.13 0.54 0.53 0.45 1.74 -0.15 -0.45 -0.14 ... -0.273 1.468 -0.734 -0.188 -0.30 -0.24 -0.19 -15.94 1.14 3
1983 1386.0 0.1 4.24 1.52 0.54 -0.00 0.82 0.35 -0.45 4.82 ... 0.043 2.425 -0.034 -0.058 1.25 0.14 -0.04 3.12 1.38 3
1984 1003.0 -0.6 -0.95 -1.17 -0.90 -0.78 -0.28 -0.37 0.46 -2.62 ... -0.443 -0.705 -0.703 -0.329 -2.65 -0.25 -0.45 -17.97 -1.89 1
1985 761.0 -0.6 -1.27 -1.02 -0.91 -0.95 -0.11 -0.30 0.04 -1.59 ... -0.328 -0.885 -0.519 -0.133 -0.62 -0.55 -0.09 14.04 0.25 3
1986 676.0 1.6 -1.08 -0.45 -0.31 -0.19 -0.31 -0.59 0.41 -1.99 ... -0.082 -0.028 -1.520 -0.266 -4.37 -0.57 -0.26 -2.15 -0.17 0
1987 779.0 -1.8 0.98 0.86 0.92 0.40 2.08 0.62 0.42 3.12 ... 0.021 1.885 0.964 0.198 2.34 0.40 -0.03 -21.47 0.58 1
1988 1394.0 0.1 -1.66 -2.18 -1.74 -0.88 -1.11 0.34 0.73 -0.30 ... 0.052 -1.547 0.888 0.158 1.71 0.25 -0.11 0.42 -0.41 2
1989 2396.0 1.2 -1.08 -0.32 -0.59 -0.92 -0.74 -0.17 0.31 -1.84 ... -0.239 -0.716 0.750 0.082 0.35 -0.32 -0.22 -9.38 -0.46 3
And only made this codes..
# uplaod dataset
X = pd.read_csv('june_index.csv')
X.set_index('Unnamed: 0', inplace=True)
# X = X.T
# X = X[['SF 10.7']]# 첫번째 인덱스만 뽑음
raw_data = pd.read_csv('jul_aug_TC_sum.csv')
y = raw_data.iloc[30:60, -1]
ind = X.index
y = pd.DataFrame(y.values, index=ind, columns=['counts'])
df = pd.concat([X,y], axis=1)
I have no clue what kind of deep learning library models i'd better use (ex. keras, pytorch or something like this)
So I need kinda recommendation or advices from RNN experts. I'm dying to wait for you guys' priceless idea.