add processing step doc

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 
-from src.components import faq, footer, form, presentation, analysis
+from src.components import faq, footer, form, presentation, analysis, docs
 from src.utils import convert_df, get_logo, read_file
 
 # app configs
@@ -42,6 +42,7 @@ if not uploaded_fl:
 else:
     df = read_file(uploaded_fl)
     outputs = form(df)
+    docs()
 
     # change or create session state
     if outputs is not None or "outputs" not in st.session_state:

src/components.py

@@ -8,6 +8,23 @@ from src.wordifier import input_transform, output_transform, wordifier
 from src.utils import get_col_indices
 
 
+def docs():
+    steps_options = list(PreprocessingPipeline.pipeline_components().keys())
+
+    with st.expander("Documentation for the Advanced Options"):
+        component_name = st.selectbox(
+            "Select a processing step to see docs",
+            options=[""] + steps_options,
+            index=1,
+            format_func=lambda x: x.replace("_", " ").title(),
+            help="Select a processing step to see the relative documentation",
+        )
+
+        pipe_component = PreprocessingPipeline.pipeline_components().get(component_name)
+        if pipe_component is not None:
+            st.help(pipe_component)
+
+
 def form(df):
     st.subheader("Parameters")
     with st.form("Wordify form"):
@@ -43,6 +60,7 @@ def form(df):
 
             if not disable_preprocessing:
                 steps_options = list(PreprocessingPipeline.pipeline_components().keys())
+
                 pre_steps = st.multiselect(
                     "Select pre-lemmatization processing steps (ordered)",
                     options=steps_options,

src/preprocessing.py

@@ -25,6 +25,7 @@ def normalize_acronyms(t: str) -> str:
 
 _re_non_word = re.compile(r"\W")
 def remove_non_word(t: str) -> str:
+    "Removes non-words characters from the text using the regex `\W`"
     return _re_non_word.sub(" ", t)
 
 
@@ -52,6 +53,7 @@ def normalize_repeating_words(t: str) -> str:
 
 
 def lowercase(t: str) -> str:
+    "Lowercases the text"
     return t.lower()