update descriptions

app.py

@@ -6,19 +6,19 @@ import pandas as pd
 
 
 description = """
-# 🧠 Neuro-Synth
+# 🧠 NeuroSynth
 
 <!-- Provide a quick summary of the dataset. -->
 
-Neuro-Synth is a synthetic neuroimaging dataset ...
+NeuroSynth is a dataset which consists of 18,000 synthetic neuroimaging data samples covering worldwide healthy population across human lifespan.
 
 ## Dataset Details
 
 The dataset has the following characteristics:
 
-* 
-* 
-* 
+* Generative models were trained on 40,000 subjects from the iSTAGING consortium to synthesize 145 brain anatomical region-of-interest (ROI) volumes which are derived from structural T1-weighted magnetic resonance imaging (MRI).
+* The dataset includes participants’ demographic information, such as sex, age and race, which are beneficial for research focusing on mitigating algorithmic bias and promoting fairnes.
+* Besides 18,000 samples in the dataset, we also share the pre-trained generative models for users to customize their needs for data synthesis. 
 
 ## Dataset Download
 
@@ -26,9 +26,9 @@ The dataset has the following characteristics:
 * Other browser users can directly click on the "Download" button to save the data
 * Download via command line:
 ```
-wget https://rongguangw-neuro-synth.hf.space/file=dataset/synth_kde_all.csv
+wget https://rongguangw-neuro-synth.hf.space/file=dataset/neurosynth_dataset.csv
 ```
-* You can also customize the number of samples by generating online in the below panels. The synthesized data will be showing in the lower right panel, and then, you can save the data by clicking on the "Download" button.
+* You can also customize sex and race for the subjects and sample size by generating online in the below panels. The synthesized data will be showing in the lower right panel, and then, you can save the data by clicking on the "Download" button.
 """
 
 citation = """
@@ -45,21 +45,20 @@ citation = """
 ```
 """
 
-file_name = "dataset/synth_kde_all.csv"
-save_name = "dataset/customized_neuro_synth.csv"
+file_name = "dataset/neurosynth_dataset.csv"
+save_name = "dataset/customized_neurosynth.csv"
 example_df = pd.read_csv(file_name)
 
 
-def infer(sex, race, num_sample):
-    #print(sex, race, num_sample)
+def infer(sex, race, num_sample=10):
     num_sample = int(num_sample)
     col_dict = np.load("model/col_dict.npz", allow_pickle=True)['dict'].item()
-    input = np.load("model/kde_{}_{}.npz".format(race.lower(), sex.lower()), allow_pickle=True)['model'].item() # "model/kde_white_female.npz"
+    input = np.load("model/kde_{}_{}.npz".format(race.lower(), sex.lower()), allow_pickle=True)['model'].item()
     kde, scaler, cols_names = input['model'], input['scaler'], input['columns']
     
     sample = kde.sample(num_sample, random_state=0)
     sample = scaler.inverse_transform(sample)
-    cov_list = np.array([[f'Synth_{i+1}', sex[0], race] for i in range(num_sample)]) # 'F', 'White'
+    cov_list = np.array([[f'Synth_{i+1}', sex[0], race] for i in range(num_sample)])
     new_data = np.concatenate([cov_list, sample], axis=1)
     cols=['PTID','Sex','Race','Age']
     cols.extend([col_dict[i] for i in fnmatch.filter(cols_names,'H_*')])
@@ -96,13 +95,11 @@ with gr.Blocks() as demo:
                 interactive=True,
                 ),
                 gr.Textbox(
-                label='Generate samples',
+                label='Number of subject',
                 show_label=True,
-                placeholder='Enter sample number (in integer)...'
+                placeholder='Enter sample size (in integer) ...'
                 )],
-            #title='Customized data generation',
             outputs=["dataframe", "button"],
-            #description='',
             cache_examples=False
         )