I'm learning neural networks and I copied a code example but I'm not sure why do I get an error. Here is my code
df = pd.read_csv('games.csv')
df =df.dropna()
X = df[['Goals', 'Saves', 'Wins', 'Games']]
Y = df['Shots']
seed = 7
numpy.random.seed(seed)
# define 10-fold cross validation test harness
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed)
cvscores = []
for train, test in kfold.split(X, Y):
model = Sequential()
model.add(Dense(16, input_dim=4, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# Fit the model
model.fit(X[train], Y[train], epochs=150, batch_size=10, verbose=0)
# evaluate the model
scores = model.evaluate(X[test], Y[test], verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
cvscores.append(scores[1] * 100)
print("%.2f%% (+/- %.2f%%)" % (numpy.mean(cvscores), numpy.std(cvscores)))
The error I get is
raise KeyError(f"None of [{key}] are in the [{axis_name}]")
KeyError: "None of [Int64Index([ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,\n ...\n 3088, 3089, 3090, 3091, 3092, 3093, 3094, 3095, 3096, 3097],\n dtype='int64', length=2788)] are in the [columns]"
Example of X because df is too big with over a hundred columns
Saves Games Wins Goals
82.60 0.765 0.51140 0.5492
86.40 0.56100 0.4902 0.71860
75.60 0.45620 0.5152 0.87820
87.00 0.52400 0.5266 0.63940
82.40 0.51180 0.5176 0.74600
80.80 0.50380 0.4976 0.79380
87.00 0.54580 0.4934 0.81160
80.25 0.46050 0.5070 0.72550
88.80 0.48180 0.5130 0.63440
78.20 0.49500 0.4920 0.75160
81.60 0.50640 0.4700 0.77280
80.60 0.49520 0.5546 0.79960
83.60 0.46060 0.5070 0.74940
83.40 0.45920 0.4428 0.75200
84.40 0.51420 0.5026 0.72400
80.40 0.50260 0.4554 0.73640
83.00 0.49375 0.4475 0.74725
79.80 0.47880 0.4898 0.78160
