changes for the presentation

.gitignore

@@ -5,4 +5,5 @@ __pycache__/
 *.hd5
 *.png
 logs/
-.ipynb_checkpoints/
+.ipynb_checkpoints/
+*.pdf

kerastest.py

@@ -25,8 +25,9 @@ X = np.array([[s.mcode, s.wpcode, s.wtcode, s.gammacode, s.alphacode, s.vcode] f
 scaler = StandardScaler()
 scaler.fit(X)
 x = scaler.transform(X)
-print(x)
+print(x.shape)
 Y = np.array([s.water_retention_both for s in train_data])
+print(Y.shape)
 X_test = np.array([[s.mcode, s.wpcode, s.wtcode, s.gammacode, s.alphacode, s.vcode] for s in test_data])
 Y_test = np.array([s.water_retention_both for s in test_data])
 tbCallBack = keras.callbacks.TensorBoard(log_dir='./logs', histogram_freq=0, batch_size=32, write_graph=True,
@@ -34,21 +35,19 @@ tbCallBack = keras.callbacks.TensorBoard(log_dir='./logs', histogram_freq=0, bat
                                          embeddings_layer_names=None, embeddings_metadata=None, embeddings_data=None,
                                          update_freq='epoch')
 
-if os.path.exists("model.hd5"):
+if os.path.exists("model.hd5") and False:
     model = load_model("model.hd5")
 else:
 
     model = Sequential()
     model.add(Dense(6, input_dim=6, kernel_initializer='normal', activation='relu'))
-    model.add(Dense(3, kernel_initializer='normal', activation='relu'))
+    model.add(Dense(4, kernel_initializer='normal', activation='relu'))
     model.add(Dense(1, kernel_initializer='normal'))
     model.compile(loss='mean_squared_error', optimizer='adam')
 
     model.summary()
     plot_model(model, "model.png", show_shapes=True, show_layer_names=True)
-
-    model.fit(x, Y, epochs=200, callbacks=[tbCallBack], validation_split=0.05)
-
+    model.fit(x, Y, epochs=200, callbacks=[tbCallBack], validation_split=0.02)
     loss = model.evaluate(X_test, Y_test)
     print(loss)
 
@@ -73,5 +72,5 @@ outgrid = np.reshape(testoutput, (100, 100))
 
 plt.pcolormesh(xgrid, ygrid, outgrid, cmap="Blues", vmin=0, vmax=1)
 plt.colorbar()
-plt.savefig("keras.png")
+plt.savefig("keras.png", transparent=True)
 plt.show()

pcatests/stack_analysis.py

@@ -2,6 +2,7 @@ import numpy as np
 from matplotlib import pyplot as plt
 from sklearn.decomposition import PCA
 from sklearn.preprocessing import StandardScaler
+
 np.set_printoptions(linewidth=1000, edgeitems=4)
 
 
@@ -33,6 +34,9 @@ print(pca.explained_variance_)  # n largest eigenvalues of covariance matrix
 print(pca.explained_variance_ratio_, "(as ratio)")
 print_heading("covariance")  ############################
 
+cov = np.cov(x.T)
+print(pca.get_covariance())
+print(np.allclose(pca.get_covariance(),cov))
 print(pca.get_covariance().shape)  # eigenvectors
 print(pca.get_covariance())
 
@@ -60,7 +64,7 @@ plt.show()
 # plot correclation matrix
 cov = pca.get_covariance()
 plt.matshow(cov)
-plt.xticks(range(len(labels)), labels,rotation=90)
+plt.xticks(range(len(labels)), labels, rotation=90)
 plt.yticks(range(len(labels)), labels)
 plt.colorbar()
 

requirements.txt

@@ -13,7 +13,6 @@ matplotlib==3.0.2
 mock==2.0.0
 numpy==1.16.1
 pbr==5.1.2
-pkg-resources==0.0.0
 protobuf==3.6.1
 pydot==1.4.1
 pyparsing==2.3.1

simulation_list.py

@@ -46,9 +46,11 @@ class SimulationList:
     def as_matrix(self):
         entrylist = []
         for sim in self.simlist:
-            entrylist.append([sim.mcode, sim.wpcode, sim.wtcode, sim.gammacode, sim.alphacode, sim.vcode,sim.water_retention_both])
+            entrylist.append(
+                [sim.mcode, sim.wpcode, sim.wtcode, sim.gammacode, sim.alphacode, sim.vcode, sim.water_retention_both]
+            )
         return np.asarray(entrylist)
 
     @property
     def matrix_labels(self):
-        return ["mcode", "wpcode", "wtcode", "gammacode", "alphacode", "vcode"]
+        return ["mcode", "wpcode", "wtcode", "gammacode", "alphacode", "vcode", "water retention"]

sliders.py

@@ -40,7 +40,7 @@ mcode_default, gamma_default, wt_default, wp_default = [24.0, 1, 10.0, 10.0]
 datagrid = get_data(mcode_default, gamma_default, wt_default, wp_default)
 
 mesh = plt.pcolormesh(grid_x, grid_y, datagrid, cmap="Blues", vmin=0, vmax=1)  # type:QuadMesh
-
+plt.colorbar()
 print(type(mesh))
 
 axcolor = 'lightgoldenrodyellow'
@@ -75,15 +75,4 @@ s_mcode.on_changed(update)
 s_wp.on_changed(update)
 s_wt.on_changed(update)
 
-# resetax = plt.axes([0.8, 0.025, 0.1, 0.04])
-# button = Button(resetax, 'Reset', color=axcolor, hovercolor='0.975')
-# 
-
-# def reset(event):
-#     sfreq.reset()
-#     samp.reset()
-# 
-# 
-# button.on_clicked(reset)
-
 plt.show()

visualize.py

@@ -27,8 +27,10 @@ plt.title("m={:3.0f}, gamma={:3.1f}, wt={:2.0f}, wp={:2.0f}\n".format(mcode, gam
 
 # plt.contourf(grid_x, grid_y, grid_c, N, cmap="Blues", vmin=0, vmax=1)
 plt.pcolormesh(grid_x, grid_y, grid_c, cmap="Blues", vmin=0, vmax=1)
-plt.colorbar().set_label("test")
-
-plt.scatter(data[:, 0], data[:, 1], c="black", cmap="Blues")
-plt.savefig("vis.png")
+plt.colorbar().set_label("water retention")
+# plt.scatter(data[:, 0], data[:, 1], c=values, cmap="Blues")
+plt.xlabel("impact angle $\\alpha$")
+plt.ylabel("velocity $v$")
+plt.tight_layout()
+plt.savefig("vis.png",transparent=True)
 plt.show()