Python linear model and neural network

group5/Neural Network.py

+#!/usr/bin/env python3
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import csv
+from datetime import datetime, timedelta
+
+from keras.models import Sequential
+from keras.layers import Dense,Dropout,BatchNormalization, Conv2D
+from keras import optimizers
+from keras import backend as K
+
+from sklearn.model_selection import train_test_split
+import sklearn
+from sklearn.metrics import mean_squared_error
+from sklearn.preprocessing import MinMaxScaler
+import os 
+import sys
+
+df = pd.read_csv("../../data/LUCAS_full/LUCAS.csv",header=0)
+
+columns = ["SOC","clay","CaCO3"]
+out_data = df[columns].values
+input_data = df[df.columns[4:]].values
+
+def is_window(column):
+    without_x = column[1:]
+    x = int(without_x)
+    if x > 1350 and x < 1450:
+        print(x)
+        return False
+    if x > 1850 and x < 2050:
+        print(x)
+        return False
+    return True
+
+input_data = df[df.columns[4:]]
+#input_data = input_data[[c for c in input_data.columns if is_window(c)]]
+
+input_data = input_data.values
+max_values = np.max(input_data, axis=1)
+
+#for idx, max_value in enumerate(max_values):
+#    input_data[idx] = input_data[idx] / max_value
+
+
+# input_train = input_data[:int(0.7*len(input_data))]
+# input_test = input_data[int(0.7*len(input_data)):]
+
+# output_train = out_data[:int(0.7*len(out_data))]
+# output_test = out_data[int(0.7*len(out_data)):]
+
+
+input_train, input_test, output_train, output_test = train_test_split(input_data, out_data, test_size=0.3, shuffle= True)
+
+K.clear_session()
+
+
+model = Sequential()
+model.add(BatchNormalization(input_shape=(input_train.shape[1],)))
+model.add(Dense(64, activation="selu"))
+model.add(Dense(128, activation="selu"))
+model.add(Dense(3, activation="selu"))
+
+
+#model.compile(optimizer="RMSprop", loss="mean_squared_error")
+model.compile(optimizer="adam", loss="mean_squared_error")
+
+model.fit(input_train,output_train,epochs=200,batch_size=32)
+
+calculated_cal = model.predict(input_train)
+calculated_val = model.predict(input_test)
+
+for i in range(len(columns)):
+    rmse_train = np.sqrt(mean_squared_error(output_train[:,i],calculated_cal[:,i]))
+    rmse_val = np.sqrt(mean_squared_error(output_test[:,i],calculated_val[:,i]))
+    R2_train=sklearn.metrics.r2_score(output_train[:,i],calculated_cal[:,i])
+    R2_val=sklearn.metrics.r2_score(output_test[:,i],calculated_val[:,i])
+
+
+
+    print("Overall:")
+    print(columns[i])
+    print(R2_train)
+    print(R2_val)
+
+import pdb
+pdb.set_trace()

group5/Neural_Network_with_linear_model.py

+#!/usr/bin/env python3
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import csv
+from datetime import datetime, timedelta
+
+from keras.models import Sequential
+from keras.layers import Dense,Dropout,BatchNormalization, Conv2D
+from keras import optimizers
+from keras import backend as K
+
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+import sklearn
+from sklearn.metrics import mean_squared_error
+from sklearn.preprocessing import MinMaxScaler
+import os 
+import sys
+
+df = pd.read_csv("../../data/LUCAS_full/LUCAS.csv",header=0)
+
+columns = ["SOC","clay","CaCO3"]
+out_data = df[columns].values
+input_data = df[df.columns[4:]].values
+
+def is_window(column):
+    without_x = column[1:]
+    x = int(without_x)
+    if x > 1350 and x < 1450:
+        print(x)
+        return False
+    if x > 1850 and x < 2050:
+        print(x)
+        return False
+    return True
+
+input_data = df[df.columns[4:]]
+#input_data = input_data[[c for c in input_data.columns if is_window(c)]]
+
+input_data = input_data.values
+
+#for idx, max_value in enumerate(max_values):
+#    input_data[idx] = input_data[idx] / max_value
+
+
+# input_train = input_data[:int(0.7*len(input_data))]
+# input_test = input_data[int(0.7*len(input_data)):]
+
+# output_train = out_data[:int(0.7*len(out_data))]
+# output_test = out_data[int(0.7*len(out_data)):]
+
+
+input_train, input_test, output_train, output_test = train_test_split(input_data, out_data, test_size=0.3, shuffle= True)
+
+reg = LinearRegression().fit(input_train, output_train)
+reg_output = reg.predict(input_train)
+ressiduals = reg_output - output_train
+
+K.clear_session()
+
+
+model = Sequential()
+model.add(BatchNormalization(input_shape=(input_train.shape[1],)))
+model.add(Dense(64, activation="selu"))
+model.add(Dense(128, activation="selu"))
+model.add(Dense(3, activation="selu"))
+
+
+#model.compile(optimizer="RMSprop", loss="mean_squared_error")
+model.compile(optimizer="adam", loss="mean_squared_error")
+
+model.fit(input_train,ressiduals,epochs=200,batch_size=32)
+
+calculated_cal = model.predict(input_train) + reg.predict(input_train)
+calculated_val = model.predict(input_test) + reg.predict(input_test)
+
+for i in range(len(columns)):
+    rmse_train = np.sqrt(mean_squared_error(output_train[:,i],calculated_cal[:,i]))
+    rmse_val = np.sqrt(mean_squared_error(output_test[:,i],calculated_val[:,i]))
+    R2_train=sklearn.metrics.r2_score(output_train[:,i],calculated_cal[:,i])
+    R2_val=sklearn.metrics.r2_score(output_test[:,i],calculated_val[:,i])
+
+
+
+    print("Overall:")
+    print(columns[i])
+    print(R2_train)
+    print(R2_val)
+
+import pdb
+pdb.set_trace()