fix: improvements to the doppelganger model

Author: ricardodcpereira

data/fcc_mba.csv

@@ -10,11 +10,11 @@ DoppelGANger is a model that uses a Generative Adversarial Network (GAN) framewo
 
 - 📑 **Paper:** [Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions](https://dl.acm.org/doi/pdf/10.1145/3419394.3423643)
 
-Here’s an example of how to synthetize time-series data with DoppelGANger using the [Yahoo Stock Price](https://www.kaggle.com/datasets/arashnic/time-series-forecasting-with-yahoo-stock-price) dataset:
+Here’s an example of how to synthetize time-series data with DoppelGANger using the [Measuring Broadband America](https://www.fcc.gov/reports-research/reports/measuring-broadband-america/raw-data-measuring-broadband-america-seventh) dataset:
 
 
 ```python
---8<-- "examples/timeseries/stock_doppelganger.py"
+--8<-- "examples/timeseries/mba_doppelganger.py"
 ```
 
 

docs/examples/doppelganger_example.md

@@ -35,23 +35,30 @@ The following example showcases how to synthesize the [Yahoo Stock Price](https:
     ```python
         # Import the necessary modules
         import pandas as pd
-        from ydata_synthetic.synthesizers import ModelParameters
-        from ydata_synthetic.synthesizers.timeseries import TimeGAN
-        from ydata_synthetic.preprocessing.timeseries.utils import real_data_loading
+        from ydata_synthetic.synthesizers.timeseries import TimeSeriesSynthesizer
+        from ydata_synthetic.synthesizers import ModelParameters, TrainParameters
 
-        # Load and preprocess data
-        stock_data_df = pd.read_csv("stock_data.csv")
-        processed_data = real_data_loading(stock_data_df.values, seq_len=24)
-       
-        # Define model and training parameters
-        gan_args = ModelParameters(batch_size=128, lr=5e-4, noise_dim=128, layers_dim=128)
-        synth = TimeGAN(model_parameters=gan_args, hidden_dim=24, seq_len=24, n_seq=6, gamma=1)
+        # Define model parameters
+        gan_args = ModelParameters(batch_size=128,
+                                lr=5e-4,
+                                noise_dim=32,
+                                layers_dim=128,
+                                latent_dim=24,
+                                gamma=1)
 
-        # Train the generator model
-        synth.train(data=processed_data, train_steps=50000)
+        train_args = TrainParameters(epochs=50000,
+                                    sequence_length=24,
+                                    number_sequences=6)
+
+        # Read the data
+        stock_data = pd.read_csv("stock_data.csv")
+
+        # Training the TimeGAN synthesizer
+        synth = TimeSeriesSynthesizer(modelname='timegan', model_parameters=gan_args)
+        synth.fit(stock_data, train_args, num_cols=list(stock_data.columns))
 
-        # Generate new synthetic data
-        synth_data = synth.sample(len(stock_data_df))
+        # Generating new synthetic samples
+        synth_data = synth.sample(n_samples=500)
     ```
 
 ## Running the Streamlit App

docs/getting-started/quickstart.md

@@ -0,0 +1,63 @@
+"""
+    DoppelGANger architecture example file
+"""
+
+# Importing necessary libraries
+import pandas as pd
+from os import path
+import matplotlib.pyplot as plt
+from ydata_synthetic.synthesizers.timeseries import TimeSeriesSynthesizer
+from ydata_synthetic.synthesizers import ModelParameters, TrainParameters
+
+# Read the data
+mba_data = pd.read_csv("../../data/fcc_mba.csv")
+numerical_cols = ["traffic_byte_counter", "ping_loss_rate"]
+categorical_cols = [col for col in mba_data.columns if col not in numerical_cols]
+
+# Define model parameters
+model_args = ModelParameters(batch_size=100,
+                             lr=0.001,
+                             betas=(0.2, 0.9),
+                             latent_dim=20,
+                             gp_lambda=2,
+                             pac=1)
+
+train_args = TrainParameters(epochs=400, sequence_length=56,
+                             sample_length=8, rounds=1,
+                             measurement_cols=["traffic_byte_counter", "ping_loss_rate"])
+
+# Training the DoppelGANger synthesizer
+if path.exists('doppelganger_mba'):
+    model_dop_gan = TimeSeriesSynthesizer.load('doppelganger_mba')
+else:
+    model_dop_gan = TimeSeriesSynthesizer(modelname='doppelganger', model_parameters=model_args)
+    model_dop_gan.fit(mba_data, train_args, num_cols=numerical_cols, cat_cols=categorical_cols)
+    model_dop_gan.save('doppelganger_mba')
+
+# Generate synthetic data
+synth_data = model_dop_gan.sample(n_samples=600)
+synth_df = pd.concat(synth_data, axis=0)
+
+# Create a plot for each measurement column
+plt.figure(figsize=(10, 6))
+
+plt.subplot(2, 1, 1)
+plt.plot(mba_data['traffic_byte_counter'].reset_index(drop=True), label='Real Traffic')
+plt.plot(synth_df['traffic_byte_counter'].reset_index(drop=True), label='Synthetic Traffic', alpha=0.7)
+plt.xlabel('Index')
+plt.ylabel('Value')
+plt.title('Traffic Comparison')
+plt.legend()
+plt.grid(True)
+
+plt.subplot(2, 1, 2)
+plt.plot(mba_data['ping_loss_rate'].reset_index(drop=True), label='Real Ping')
+plt.plot(synth_df['ping_loss_rate'].reset_index(drop=True), label='Synthetic Ping', alpha=0.7)
+plt.xlabel('Index')
+plt.ylabel('Value')
+plt.title('Ping Comparison')
+plt.legend()
+plt.grid(True)
+
+plt.tight_layout()
+plt.show()