making small text changes

app.py

@@ -50,7 +50,7 @@ with st.sidebar.expander("Datasets", expanded=True):
         sorted(top_datasets))
     configs = get_dataset_config_names(dataset_name)
     dataset_config = st.selectbox(
-        f"Choose a configuration of your dataset:",
+        f"Choose a configuration of the dataset:",
         configs)
     dataset_builder = load_dataset_builder(dataset_name, dataset_config)
     splits = [s for s in dataset_builder.info.splits]
@@ -61,7 +61,7 @@ with st.sidebar.expander("Datasets", expanded=True):
 
 
 
-st.markdown("## Here is some information about your dataset:")
+st.markdown("## Here is some information about this dataset:")
 
 
 st.markdown(dataset_builder.info.description)
@@ -74,7 +74,7 @@ st.markdown("## Now let's see what metrics we can use to evaluate models on this
 
 st.markdown("### Dataset-Specific Metrics")
 if dataset_name in metrics:
-    st.markdown("Great news! Your dataset has a dedicated metric for it!:partying_face: You can use it like this: :point_down:")
+    st.markdown("Great news! This dataset has a dedicated metric for it!:partying_face: You can use it like this: :point_down:")
     if "glue" in dataset_name:
         code = ''' from datasets import load_metric
      metric = load_metric(\"'''+dataset_name+'''\", \"'''+dataset_config+'''\")'''
@@ -84,7 +84,7 @@ if dataset_name in metrics:
      metric = load_metric(\"'''+dataset_name+'''\")'''
         st.code(code, language='python')
 else:
-    st.markdown("Your dataset doesn't have a dedicated metric, but that's ok! :wink:")
+    st.markdown("This dataset doesn't have a dedicated metric, but that's ok! :wink:")
     dedicated_metric = False
 
 st.markdown("### Task-Specific Metrics")
@@ -92,7 +92,7 @@ st.markdown("### Task-Specific Metrics")
 task = find_task(dataset_name)
 
 if task is not None:
-    st.markdown("The task associated to it your dataset is: " + task.replace('-',' '))
+    st.markdown("The task associated to it this dataset is: " + task.replace('-',' '))
     if task == 'automatic-speech-recognition':
         st.markdown('Automatic Speech Recognition has some dedicated metrics such as:')
         st.markdown('[Word Error Rate](https://huggingface.co/metrics/wer)')
@@ -104,7 +104,7 @@ if task is not None:
     metric = load_metric("cer")'''
         st.code(cer_code, language='python')
 else:
-    st.markdown("The task for your dataset doesn't have any dedicated metrics, but you can still use general ones! :cowboy_hat_face:")
+    st.markdown("The task for this dataset doesn't have any dedicated metrics, but you can still use general ones! :cowboy_hat_face:")
 
 
 #print(dataset_builder.info.task_templates)
@@ -130,7 +130,7 @@ try:
     labels = labels.rename(columns={"count_star()": "count"})
     labels.index = dataset_builder.info.features['label'].names
     st.markdown("### Labelled  Metrics")
-    st.markdown("Your dataset has "+ str(dataset_builder.info.features['label'].num_classes) + " labels : " + ', '.join(dataset_builder.info.features['label'].names))
+    st.markdown("This dataset has "+ str(dataset_builder.info.features['label'].num_classes) + " labels : " + ', '.join(dataset_builder.info.features['label'].names))
     #TODO : figure out how to make a label plot
     st.plotly_chart(px.pie(labels, values = "count", names = labels.index, width=800, height=400))
     total = sum(c for c in labels['count'])
@@ -138,14 +138,14 @@ try:
     #proportion = [0.85, 0.15]
     stdev_dataset= statistics.stdev(proportion)
     if stdev_dataset <= balanced_stdev:
-            st.markdown("Since your dataset is well-balanced (with a standard deviation of " + str(round(stdev_dataset,2)) +"), you can look at using:")
+            st.markdown("Since this dataset is well-balanced (with a standard deviation of " + str(round(stdev_dataset,2)) +"), you can look at using:")
             st.markdown('[Accuracy](https://huggingface.co/metrics/accuracy)')
             accuracy_code = '''from datasets import load_metric
         metric = load_metric("accuracy")'''
             st.code(accuracy_code, language='python')
 
     else:
-            st.markdown("Since your dataset is not well-balanced (with a standard deviation of " + str(round(stdev_dataset,2)) +"), you can look at using:")
+            st.markdown("Since this dataset is not well-balanced (with a standard deviation of " + str(round(stdev_dataset,2)) +"), you can look at using:")
             st.markdown('[F1 Score](https://huggingface.co/metrics/f1)')
             accuracy_code = '''from datasets import load_metric
         metric = load_metric("accuracy")'''
@@ -154,7 +154,7 @@ try:
 except:
     if task != 'automatic-speech-recognition':
         st.markdown("### Unsupervised  Metrics")
-        st.markdown("Since dataset doesn't have any labels, so the metrics that you can use for evaluation are:")
+        st.markdown("Since this dataset doesn't have any labels, the metrics that you can use for evaluation are:")
         st.markdown('[Perplexity](https://huggingface.co/metrics/perplexity)')
         perplexity_code = '''from datasets import load_metric
     metric = load_metric("perplexity")'''