Made more readyable and added plots

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import matplotlib.pyplot as plt
 import numpy as np
+from functools import partial
 
 # ai4code_ds = load_dataset("CarperAI/pile-v2-small", data_dir="data/AI4Code")
 # amps_ds = load_dataset("CarperAI/pile-v2-small", data_dir="data/AMPS")
@@ -182,57 +183,52 @@ dataset_data = {
     },
 }
 
-def plt_plot(threshold, x):
-    # prepare some data for a histogram
-    # x = np.random.randn(1000)
+def plt_plot(ratio, dataset, threshold):
+    x = dataset_data[dataset][ratio]
+    # calculate percentage of data that will be removed given threshold
+    perc = np.sum(x < threshold) / len(x)
     # create a figure
     fig = plt.figure()
     # add a subplot
     ax = fig.add_subplot(111)
-    # plot some data
-    ax.hist(x, bins=50)
+    # plot some data using black
+    ax.hist(x, bins=50, color="black")
     # plot red dashed line at threshold
     ax.axvline(threshold, color='r', linestyle='dashed', linewidth=2)
-    plt.title("Histogram of random data")
+    # set title
+    # add percentage of data removed
+    ax.set_title(f"{dataset} (removed {perc:.2%})")
     plt.xlabel("Value")
     plt.ylabel("Frequency")
+    # make it look nice
+    plt.tight_layout()
     return fig
-    # x = ["Math", "Business", "Statistics", "IT", "Commerce"]
-    # y = [68, 73, 82, 74, 85]
-    # # create a new plot
-    # plt.rcParams['figure.figsize'] = 6,4
-    # fig = plt.figure()
-    # ax = fig.add_axes([0,0,1,1])
-    # ax.bar(x, y)
-    # plot red dashed line at threshold
-    # plt.axhline(y=threshold, color='r', linestyle='--')
-    # plt.title("Marks per subject")
-    # plt.xlabel("Subject")
-    # plt.ylabel("Score")
-
-    # return fig
 
 with gr.Blocks() as demo:
-    dataset = gr.Radio(list(dataset_data.keys()), label="Dataset")
+    dataset = gr.Radio(list(dataset_data.keys()), label="Dataset", value="arXiv")
+    print(dataset.value)
 
     with gr.Tab("Character Repetition Ratio"):
         # plot some random data
         plot = gr.Plot()
         threshold = gr.Slider(minimum=0, maximum=100, label="Threshold")
         calculate = gr.Button("Calculate")
-        calculate.click(plt_plot, [threshold, dataset_data[dataset].char_rep_ratios], plot)
+        plot_fn = partial(plt_plot, "word_rep_ratios")
+        calculate.click(plot_fn, [dataset, threshold], plot)
     
     with gr.Tab("Word Repetition Ratio"):# plot some random data
         plot = gr.Plot()
         threshold = gr.Slider(minimum=0, maximum=1, label="Threshold")
         calculate = gr.Button("Calculate")
-        calculate.click(plt_plot, [threshold, dataset_data[dataset].word_rep_ratios], plot)
+        plot_fn = partial(plt_plot, "char_rep_ratios")
+        calculate.click(plot_fn, [dataset, threshold], plot)
     
     with gr.Tab("Flagged Word Ratio"):# plot some random data
         plot = gr.Plot()
         threshold = gr.Slider(minimum=0, maximum=1, label="Threshold")
         calculate = gr.Button("Calculate")
-        calculate.click(plt_plot, [threshold, dataset_data[dataset].flagged_word_ratios], plot)
+        plot_fn = partial(plt_plot, "flagged_word_ratios")
+        calculate.click(plot_fn, [dataset, threshold], plot)
 
 if __name__ == "__main__":
     demo.launch(share=True)