Just put everything together for the appendum. The README should expl…

…ain mostly everything that it needs. All the data and scripts have been modified to use relative paths, rather than absolute. Using best configuration of the GAN. Created a requirement.txt for python dependency installing.

README.md

@@ -0,0 +1,57 @@
+Data Wrangling & GAN
+=================================
+
+## R Dependencies
+
+When using R I like using [RStudio](https://www.rstudio.com). I think it's the best IDE for R, and makes iterating on code very easy and quick. Within RStudio there is a package manager that can help you install the packages I have listed here:
+
+* dyplr
+* ggplot2
+
+The following two packages are installed a little differently.
+First install [Bioconductor](http://bioconductor.org/)
+Then you may install [GEOQuery](http://genomicsclass.github.io/book/pages/GEOquery.html)
+
+Those two packages are used in [get_gse_data.r](./mkdataset/get_gse_data.r), which can get any GSE, given the GSE ID and gene symbol column name.
+
+
+## Python Dependencies
+
+I used a virtual environment by [virtualenv](https://pypi.python.org/pypi/virtualenv). If you want to use it as well, I recommend [this installation tutorial](http://docs.python-guide.org/en/latest/dev/virtualenvs/).
+
+> **NOTE**: Using a virtual environment doesn't allows you to use [matplotlib](http://matplotlib.org/faq/virtualenv_faq.html) directly. You need to map it to your system's copy of **matplotlib** because the graphics libraries to create window frames is closely tied to the operating system.
+
+The prominent packages are:
+
+* numpy
+* Pandas
+* Scikit-Learn
+* TensorFlow
+* Keras
+* keras_adversarial
+
+To install all the dependencies quickly and easily you should use [`pip`](https://pypi.python.org/pypi/pip/)
+
+```bash
+pip install -r requirements.txt
+```
+
+## How to Run any Script
+
+Just navigate to the folder containing the script, and run it directly.
+
+### R
+
+If you're using RStudio, then all you need to do is **source** the script. There is a button for that in the top right corner of the editor window. Else from the command line:
+
+```r
+R CMD BATCH <name_of_script>
+```
+
+### Python
+
+Just run it directly from the command line. Assuming that you environment is prepared, and you have all the dependencies, all you have to do is
+
+```
+python gan.py
+```

gan/gan.py

@@ -7,8 +7,8 @@ from sklearn.cross_validation import train_test_split
 from sklearn.utils import resample
 # import matplotlib.pyplot as plt
 # Nuerual Net Building
-from keras import layers
-from keras.layers import Input, Dense, Dropout, InputLayer, Reshape
+from keras import layers, initializers, regularizers
+from keras.layers import Input, Dense, ActivityRegularization, InputLayer, Reshape, BatchNormalization, Flatten
 from keras.models import Sequential, Model
 from keras.optimizers import Adam
 from keras.utils.generic_utils import Progbar
@@ -70,101 +70,114 @@ all_data = pd.read_csv(os.path.join(base_path, file_name))
 # Prepare Data
 #---------------------------------------
 
-just_values = all_data.iloc[:, 3:]
-new_sample = permute_sample(just_values, 5)
-real_dataset = make_3d_dataset(just_values, 5, 2)
-print(real_dataset.shape)
-print(real_dataset)
-
-# # Prepare data
-# x_train = all_data.iloc[:, np.arange(20)]
-#
-# # column_start_index_of_genes = 2
-# # class_label_column_index = 1
-# # features = all_data.iloc[:, np.arange(column_start_index_of_genes, df.shape[1])]
-# # labels = all_data.iloc[:, class_label_column_index]
-#
-# # column_start_index_of_genes = 2
-# # features = all_data.iloc[:, np.arange(20)]
-# # labels = labeled_data.iloc[:, class_label_column_index]
-#
-# # x_train, x_test, y_train, y_test = train_test_split(features, labels, test_size=0.33, random_state=42)
-#
-#
-# #################################################
-# # Variables
-# #################################################
-#
-# # Output
-# output_base_path = './'
-#
-# #---------------------------------------
-# # Network Variables
-# #---------------------------------------
-#
-# input_dimension = x_train.shape[1]  # Number of features (e.g. genes)
-#
-# gen_input_shape = (input_dimension,)
-# discr_input_shape = (input_dimension,)
-#
-# epochs = 10
-# batch_size =  x_train.shape[0]
-#
-# # Build Generative model
-# generative_model = Sequential()
-# # generative_model.add(InputLayer(input_shape=gen_input_shape))
-# generative_model.add(Dense(units=int(1.2*input_dimension), activation='relu', input_dim=input_dimension))
-# generative_model.add(Dropout(rate=0.2, noise_shape=None, seed=15))
-# generative_model.add(Dense(units=int(0.2*input_dimension), activation='relu'))
-# generative_model.add(Dense(units=input_dimension, activation='relu'))
-# generative_model.add(Reshape(discr_input_shape))
-#
-# # Build Discriminator model
-# discriminator_model = Sequential()
-# discriminator_model.add(InputLayer(input_shape=discr_input_shape))
-# discriminator_model.add(Dense(units=int(1.2*input_dimension), activation='relu'))
-# discriminator_model.add(Dropout(rate=0.2, noise_shape=None, seed=75))
-# discriminator_model.add(Dense(units=int(0.2*input_dimension), activation='relu'))
-# discriminator_model.add(Dense(units=1, activation='sigmoid'))
-#
-# # Build GAN
-# gan = simple_gan(generative_model, discriminator_model, normal_latent_sampling((input_dimension, )))
-# model = AdversarialModel(base_model=gan,
-#                         player_params=[generative_model.trainable_weights,
-#                                         discriminator_model.trainable_weights],
-#                         player_names=['generator', 'discriminator'])
-# # Other optimizer to try AdversarialOptimizerAlternating
-# model.adversarial_compile(adversarial_optimizer=AdversarialOptimizerSimultaneous(),
-#                           player_optimizers=['adam', 'adam'], loss='binary_crossentropy')
-#
-# # Print Summary of Models
-# generative_model.summary()
-# discriminator_model.summary()
-# gan.summary()
-#
-# # Train
-# # gan_targets takes as inputs the # of samples
-# training_record = model.fit(x=x_train, y=gan_targets(x_train.shape[0]), epochs=epochs,
-#                             batch_size=batch_size)
-#
-# # Diplay plot of loss over training
-# # plt.plot(history.history['player_0_loss'])
-# # plt.plot(history.history['player_1_loss'])
-# # plt.plot(history.history['loss'])
-#
-# # Predict (i.e. produce new samples)
-# zsamples = np.random.normal(size=(1, input_dimension))
-# pred = generative_model.predict(zsamples)
-# print(pred)
-#
-# # Save new samples to file
-# # new_samples = pd.DataFrame(pred)
-# # new_samples.to_csv(os.path.join(output_base_path, 'new_samples.csv'))
-#
-# # # save training_record
-# # df = pd.DataFrame(training_record.history)
-# # df.to_csv(os.path.join(output_base_path, 'training_record.csv'))
-# #
-# # # save models
-# # generator.save(os.path.join(output_base_path, 'generator.h5'))
-# # discriminator.save(os.path.join(output_base_path, "discriminator.h5"))
+just_values = all_data.iloc[1:, 3:]
+x_train = make_3d_dataset(just_values, 300, 100)
+
+#################################################
+# Variables
+#################################################
+
+# Output
+output_base_path = './'
+
+#---------------------------------------
+# Network Variables
+#---------------------------------------
+
+# Layer Input Output Shapes
+gen_input_shape = (x_train.shape[1], x_train.shape[2])
+discr_input_shape = (x_train.shape[1], x_train.shape[2])
+
+gen_output_shape = discr_input_shape
+
+# Generator Variables
+weight_initializer = initializers.RandomNormal(mean=0.0, stddev=0.05, seed=None)
+bias_initializer = initializers.RandomUniform(minval=-0.05, maxval=0.05, seed=None)
+generator_regularizer = regularizers.l1(0.000000005)
+descriminator_regularizer = regularizers.l2(0.0000000005)
+
+# Training Varaibles
+epochs = 2
+batch_size = 1  # x_train.shape[0]
+input_size = x_train.shape[1] * x_train.shape[2] * batch_size
+
+# Build Generative model
+generative_model = Sequential()
+# generative_model.add(InputLayer(input_shape=gen_input_shape))
+generative_model.add(InputLayer(input_shape=discr_input_shape))
+generative_model.add(Flatten())
+generative_model.add(Dense(units=int(1.5*input_size),
+                            use_bias=True,
+                            activation='relu',
+                            kernel_initializer=weight_initializer,
+                            bias_initializer=bias_initializer,
+                            kernel_regularizer=generator_regularizer))
+# generative_model.add(ActivityRegularization(l1=0.02))
+generative_model.add(Dense(units=int(input_size),
+                            activation='relu',
+                            kernel_initializer=weight_initializer,
+                            kernel_regularizer=generator_regularizer))
+generative_model.add(Reshape(discr_input_shape))
+
+# Build Discriminator model
+discriminator_model = Sequential()
+discriminator_model.add(InputLayer(input_shape=discr_input_shape))
+discriminator_model.add(BatchNormalization(axis=1))
+discriminator_model.add(Flatten())
+discriminator_model.add(Dense(units=int(1.5*input_size),
+                            use_bias=True,
+                            activation='relu',
+                            kernel_initializer=weight_initializer,
+                            bias_initializer=bias_initializer,
+                            kernel_regularizer=descriminator_regularizer))
+# discriminator_model.add(ActivityRegularization(l2=0.02))
+discriminator_model.add(Dense(units=int(0.2*input_size),
+                                activation='relu',
+                                kernel_initializer=weight_initializer,
+                                bias_initializer=bias_initializer,
+                                kernel_regularizer=descriminator_regularizer))
+discriminator_model.add(Dense(units=1, activation='sigmoid'))
+
+# Build GAN
+gan = simple_gan(generative_model, discriminator_model, normal_latent_sampling(gen_input_shape))
+model = AdversarialModel(base_model=gan,
+                        player_params=[generative_model.trainable_weights,
+                                        discriminator_model.trainable_weights],
+                        player_names=['generator', 'discriminator'])
+# Other optimizer to try AdversarialOptimizerAlternating
+model.adversarial_compile(adversarial_optimizer=AdversarialOptimizerSimultaneous(),
+                          player_optimizers=['adam', 'adam'], loss='binary_crossentropy')
+
+# Print Summary of Models
+generative_model.summary()
+discriminator_model.summary()
+gan.summary()
+
+# Train
+# gan_targets takes as inputs the # of samples
+training_record = model.fit(x=x_train,
+                            y=gan_targets(x_train.shape[0]),
+                            epochs=epochs,
+                            batch_size=batch_size)
+
+# Diplay plot of loss over training
+# plt.plot(history.history['player_0_loss'])
+# plt.plot(history.history['player_1_loss'])
+# plt.plot(history.history['loss'])
+
+# Predict (i.e. produce new samples)
+zsamples = np.random.normal(size=(1, x_train.shape[1], x_train.shape[2]))
+pred = generative_model.predict(zsamples)
+print(pred)
+
+# Save new samples to file
+new_samples = pd.DataFrame(pred[0,:,:])
+new_samples.to_csv(os.path.join(output_base_path, 'new_samples.csv'))
+
+# save training_record
+df = pd.DataFrame(training_record.history)
+df.to_csv(os.path.join(output_base_path, 'training_record.csv'))
+
+# save models
+generative_model.save(os.path.join(output_base_path, 'generator.h5'))
+discriminator_model.save(os.path.join(output_base_path, "discriminator.h5"))