neural network predictions

Dockerfile

@@ -6,7 +6,7 @@ RUN apt install -y python3-pip
 RUN apt install -y unzip
 RUN pip3 install pandas
 RUN pip3 install kaggle
-RUN pip3 install torch
+RUN pip3 install tensorflow
 COPY ./get_data.sh ./
 COPY get_data.py ./
 COPY ./neural_network.sh ./

neural_network.py

@@ -1,8 +1,45 @@
-import torch
 import pandas as pd
-import torch.nn as nn
-import torch.nn.functional as F
-from torch.utils.data import Dataset, DataLoader
+import numpy as np
+
+from tensorflow import keras
 
 device = 'cpu'
 
+data = pd.read_csv("data_train", sep=',', error_bad_lines=False).dropna()
+X = data.loc[:,data.columns == "2805317"].astype(int)
+y = data.loc[:,data.columns == "198909"].astype(int)
+
+
+def NormalizeData(data):
+    return (data - np.min(data)) / (np.max(data) - np.min(data))
+
+
+X = NormalizeData(X)
+y = NormalizeData(y)
+
+
+model = keras.Sequential([
+    keras.layers.Dense(512,input_dim = X.shape[1],kernel_initializer='normal', activation='relu'),
+    keras.layers.Dense(512,kernel_initializer='normal', activation='relu'),
+    keras.layers.Dense(256,kernel_initializer='normal', activation='relu'),
+    keras.layers.Dense(256,kernel_initializer='normal', activation='relu'),
+    keras.layers.Dense(128,kernel_initializer='normal', activation='relu'),
+    keras.layers.Dense(1,kernel_initializer='normal', activation='linear'),
+])
+
+model.compile(loss='mean_absolute_error', optimizer='adam', metrics=['mean_absolute_error'])
+
+model.fit(X, y, epochs=30, validation_split = 0.3)
+
+data = pd.read_csv("data_test", sep=',', error_bad_lines=False).dropna()
+X_test = data.loc[:,data.columns == "2805317"].astype(int)
+y_test = data.loc[:,data.columns == "198909"].astype(int)
+
+X_test = NormalizeData(X_test)
+y_test = NormalizeData(y_test)
+
+prediction = model.predict(X_test)
+
+f = open("predictions.txt", "w")
+for (pred, test) in zip(prediction, y_test.values):
+    f.write("predicted: %s expected: %s\n" % (str(pred), str(test)))