format and delete old

app.py

@@ -1,12 +1,9 @@
 import streamlit as st
-from src.utils import get_logo
+
 from src import session_state
-from src.pages import (
-    home,
-    faq,
-    about,
-)
 from src.configs import SupportedFiles
+from src.pages import about, faq, home
+from src.utils import get_logo
 
 # app configs
 st.set_page_config(
@@ -59,7 +56,9 @@ st.sidebar.markdown(
     """,
     unsafe_allow_html=True,
 )
-st.sidebar.info("Something not working? Consider [filing an issue](https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new)")
+st.sidebar.info(
+    "Something not working? Consider [filing an issue](https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new)"
+)
 
 
 # ==== MAIN ==== #

main.py

@@ -1,7 +1,7 @@
 import streamlit as st
-from src.utils import get_logo, read_file, convert_df
-from src.components import form, faq, presentation, footer, about
 
+from src.components import about, faq, footer, form, presentation
+from src.utils import convert_df, get_logo, read_file
 
 # app configs
 st.set_page_config(
@@ -10,10 +10,10 @@ st.set_page_config(
     layout="centered",
     page_icon="./assets/logo.png",
     menu_items={
-        'Get Help': "https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new",
-        'Report a Bug': "https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new",
-        'About': about(),
-    }
+        "Get Help": "https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new",
+        "Report a Bug": "https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new",
+        "About": about(),
+    },
 )
 
 # logo

src/components.py

@@ -1,7 +1,8 @@
 import streamlit as st
+
+from src.configs import Languages, PreprocessingConfigs, SupportedFiles
 from src.preprocessing import PreprocessingPipeline
-from src.wordifier import input_transform, wordifier, output_transform
-from src.configs import PreprocessingConfigs, SupportedFiles, Languages
+from src.wordifier import input_transform, output_transform, wordifier
 
 
 @st.experimental_memo
@@ -12,10 +13,16 @@ def form(df):
 
             cols = [""] + df.columns.tolist()
             label_column = st.selectbox(
-                "Select label column", cols, index=0, help="Select the column containing the labels"
+                "Select label column",
+                cols,
+                index=0,
+                help="Select the column containing the labels",
             )
             text_column = st.selectbox(
-                "Select text column", cols, index=0, help="Select the column containing the text"
+                "Select text column",
+                cols,
+                index=0,
+                help="Select the column containing the text",
             )
             language = st.selectbox(
                 "Select language",
@@ -31,12 +38,16 @@ def form(df):
             pre_steps = st.multiselect(
                 "Select pre-lemmatization processing steps (ordered)",
                 options=steps_options,
-                default=[steps_options[i] for i in PreprocessingConfigs.DEFAULT_PRE.value],
+                default=[
+                    steps_options[i] for i in PreprocessingConfigs.DEFAULT_PRE.value
+                ],
                 format_func=lambda x: x.replace("_", " ").title(),
                 help="Select the processing steps to apply before the text is lemmatized",
             )
 
-            lammatization_options = list(PreprocessingPipeline.lemmatization_component().keys())
+            lammatization_options = list(
+                PreprocessingPipeline.lemmatization_component().keys()
+            )
             lemmatization_step = st.selectbox(
                 "Select lemmatization",
                 options=lammatization_options,
@@ -47,7 +58,9 @@ def form(df):
             post_steps = st.multiselect(
                 "Select post-lemmatization processing steps (ordered)",
                 options=steps_options,
-                default=[steps_options[i] for i in PreprocessingConfigs.DEFAULT_POST.value],
+                default=[
+                    steps_options[i] for i in PreprocessingConfigs.DEFAULT_POST.value
+                ],
                 format_func=lambda x: x.replace("_", " ").title(),
                 help="Select the processing steps to apply after the text is lemmatized",
             )
@@ -58,7 +71,9 @@ def form(df):
 
             # preprocess
             with st.spinner("Step 1/4: Preprocessing text"):
-                pipe = PreprocessingPipeline(language, pre_steps, lemmatization_step, post_steps)
+                pipe = PreprocessingPipeline(
+                    language, pre_steps, lemmatization_step, post_steps
+                )
                 df = pipe.vaex_process(df, text_column)
 
             # prepare input
@@ -188,7 +203,10 @@ def presentation():
         """
     )
     st.table(
-        {"text": ["A review", "Another review", "Yet another one", "etc"], "label": ["Good", "Bad", "Good", "etc"]}
+        {
+            "text": ["A review", "Another review", "Yet another one", "etc"],
+            "label": ["Good", "Bad", "Good", "etc"],
+        }
     )
 
     st.subheader("Output format")
@@ -226,6 +244,7 @@ def contacts():
     <iframe src="https://www.google.com/maps/embed?pb=!1m18!1m12!1m3!1d2798.949796165441!2d9.185730115812493!3d45.450667779100726!2m3!1f0!2f0!3f0!3m2!1i1024!2i768!4f13.1!3m3!1m2!1s0x4786c405ae6543c9%3A0xf2bb2313b36af88c!2sVia%20Guglielmo%20R%C3%B6ntgen%2C%201%2C%2020136%20Milano%20MI!5e0!3m2!1sit!2sit!4v1569325279433!5m2!1sit!2sit" frameborder="0" style="border:0; width: 100%; height: 312px;" allowfullscreen></iframe>
     """
 
+
 def about():
     return """
     The wordify team

src/configs.py

@@ -1,4 +1,5 @@
 from enum import Enum
+
 import pandas as pd
 
 

src/pages/about.py

@@ -1,34 +0,0 @@
-import streamlit as st
-
-
-def write(*args):
-    # ==== Contacts ==== #
-    with st.beta_container():
-        st.markdown("")
-        st.markdown("")
-        st.header(":rocket:About us")
-
-        st.markdown(
-            """
-            You can reach out to us via email, phone, or - if you are old-fashioned - via mail
-            """
-        )
-        with st.beta_expander("Contacts"):
-
-            _, col2 = st.beta_columns([0.5, 3])
-            col2.markdown(
-                """
-                :email: wordify@unibocconi.it
-
-                :telephone_receiver: +39 02 5836 2604
-
-                :postbox: Via Röntgen n. 1, Milan 20136 (ITALY)
-                """
-            )
-
-        st.write(
-            """
-            <iframe src="https://www.google.com/maps/embed?pb=!1m18!1m12!1m3!1d2798.949796165441!2d9.185730115812493!3d45.450667779100726!2m3!1f0!2f0!3f0!3m2!1i1024!2i768!4f13.1!3m3!1m2!1s0x4786c405ae6543c9%3A0xf2bb2313b36af88c!2sVia%20Guglielmo%20R%C3%B6ntgen%2C%201%2C%2020136%20Milano%20MI!5e0!3m2!1sit!2sit!4v1569325279433!5m2!1sit!2sit" frameborder="0" style="border:0; width: 100%; height: 312px;" allowfullscreen></iframe>
-            """,
-            unsafe_allow_html=True,
-        )

src/pages/faq.py

@@ -1,126 +0,0 @@
-import streamlit as st
-from src.configs import Languages
-
-
-def write(*args):
-
-    # ==== HOW IT WORKS ==== #
-    with st.beta_container():
-        st.markdown("")
-        st.markdown("")
-        st.markdown(
-            """
-            Wordify makes it easy to identify words that discriminate categories in textual data.
-
-            Let's explain Wordify with an example. Imagine you are thinking about having a glass
-            of wine :wine_glass: with your friends :man-man-girl-girl: and you have to buy a bottle.
-            You know you like `bold`, `woody` wine but are unsure which one to choose.
-            You wonder whether there are some words that describe each type of wine.
-            Since you are a researcher :female-scientist: :male-scientist:, you decide to approach
-            the problem scientifically :microscope:. That's where Wordify comes to the rescue!
-            """
-        )
-        st.markdown("")
-        st.markdown("")
-        st.header("Steps")
-        st.subheader("Step 1 - Prepare your data")
-        st.markdown(
-            """
-            Create an Excel or CSV file with two columns for each row:
-
-            - a column with the name or the label identifying a specific object or class (e.g., in our
-            wine example above it would be the type of wine or the name of a specific brand). It is
-            common practice naming this column `label`
-
-            - a column with the text describing that specific object or class (e.g., in the wine example
-            above it could be the description that you find on the rear of the bottle label). It is
-            common practice naming this column `text`
-
-            To have reliable results, we suggest providing at least 2000 labelled texts. If you provide
-            less we will still wordify your file, but the results should then be taken with a grain of
-            salt.
-
-            Consider that we also support multi-language texts, therefore you'll be able to
-            automatically discriminate between international wines, even if your preferred Italian
-            producer does not provide you with a description written in English!
-            """
-        )
-
-        st.subheader("Step 2 - Upload your file and Wordify!")
-        st.markdown(
-            """
-            Once you have prepared your Excel or CSV file, click the "Browse File" button.
-            Browse for your file.
-            Choose the language of your texts (select multi-language if your file contains text in
-            different languages).
-            Push the "Wordify|" button, set back, and wait for wordify to do its tricks.
-
-            Depending on the size of your data, the process can take from 1 minute to 5 minutes
-            """
-        )
-
-    # ==== FAQ ==== #
-    with st.beta_container():
-        st.markdown("")
-        st.markdown("")
-        st.header(":question:Frequently Asked Questions")
-        with st.beta_expander("What is Wordify?"):
-            st.markdown(
-                """
-                Wordify is a way to find out which terms are most indicative for each of your dependent
-                variable values.
-                """
-            )
-
-        with st.beta_expander("What happens to my data?"):
-            st.markdown(
-                """
-                Nothing. We never store the data you upload on disk: it is only kept in memory for the
-                duration of the modeling, and then deleted. We do not retain any copies or traces of
-                your data.
-                """
-            )
-
-        with st.beta_expander("What input formats do you support?"):
-            st.markdown(
-                """
-                The file you upload should be .xlsx, with two columns: the first should be labeled
-                'text' and contain all your documents (e.g., tweets, reviews, patents, etc.), one per
-                line. The second column should be labeled 'label', and contain the dependent variable
-                label associated with each text (e.g., rating, author gender, company, etc.).
-                """
-            )
-
-        with st.beta_expander("How does it work?"):
-            st.markdown(
-                """
-                It uses a variant of the Stability Selection algorithm
-                [(Meinshausen and Bühlmann, 2010)](https://rss.onlinelibrary.wiley.com/doi/full/10.1111/j.1467-9868.2010.00740.x)
-                to fit hundreds of logistic regression models on random subsets of the data, using
-                different L1 penalties to drive as many of the term coefficients to 0. Any terms that
-                receive a non-zero coefficient in at least 30% of all model runs can be seen as stable
-                indicators.
-                """
-            )
-
-        with st.beta_expander("How much data do I need?"):
-            st.markdown(
-                """
-                We recommend at least 2000 instances, the more, the better. With fewer instances, the
-                results are less replicable and reliable.
-                """
-            )
-
-        with st.beta_expander("Is there a paper I can cite?"):
-            st.markdown(
-                """
-                Yes please! Reference coming soon...
-                """
-            )
-
-        with st.beta_expander("What languages are supported?"):
-            st.markdown(
-                f"""
-                Currently we support: {", ".join([i.name for i in Languages])}.
-                """
-            )

src/pages/home.py

@@ -1,240 +0,0 @@
-from src.configs import Languages
-from src.utils import read_file, download_button
-from src.plotting import plot_labels_prop, plot_nchars, plot_score
-from src.preprocessing import Lemmatizer, PreprocessingPipeline, encode
-from src.wordifier import wordifier
-import streamlit as st
-
-
-def write(session, uploaded_file):
-
-    if not uploaded_file:
-        st.markdown(
-            """
-            Hi, welcome to __Wordify__! :rocket:
-
-            Start by uploading a file - CSV, XLSX (avoid Strict Open XML Spreadsheet format [here](https://stackoverflow.com/questions/62800822/openpyxl-cannot-read-strict-open-xml-spreadsheet-format-userwarning-file-conta)),
-            or PARQUET are currently supported.
-
-            Once you have uploaded the file, __Wordify__ will show an interactive UI through which
-            you'll be able to interactively decide the text preprocessing steps, their order, and
-            proceed to Wordify your text.
-
-            If you're ready, let's jump in:
-
-            :point_left: upload a file via the upload widget in the sidebar!
-
-            NOTE: whenever you want to reset everything, simply refresh the page.
-            """
-        )
-
-    elif uploaded_file:
-
-        # ==== 1. READ FILE ==== #
-        with st.spinner("Reading file"):
-            # TODO: write parser function that automatically understands format
-            data = read_file(uploaded_file)
-
-        # 2. CREATE UI TO SELECT COLUMNS
-        col1, col2, col3 = st.beta_columns(3)
-        with col1:
-            language = st.selectbox("Select language", [i.name for i in Languages])
-            with st.beta_expander("Description"):
-                st.markdown(
-                    f"Select a language amongst those supported: {', '.join([f'`{i.name}`' for i in Languages])}. This will be used to lemmatize and remove stopwords."
-                )
-        with col2:
-            cols_options = [""] + data.columns.tolist()
-            label_column = st.selectbox(
-                "Select label column name", cols_options, index=0
-            )
-            with st.beta_expander("Description"):
-                st.markdown("Select the column containing the labels.")
-
-            if label_column:
-                plot = plot_labels_prop(data, label_column)
-                if plot:
-                    st.altair_chart(plot, use_container_width=True)
-
-        with col3:
-            text_column = st.selectbox("Select text column name", cols_options, index=0)
-            with st.beta_expander("Description"):
-                st.markdown("Select the column containing the texts.")
-
-            if text_column:
-                st.altair_chart(
-                    plot_nchars(data, text_column), use_container_width=True
-                )
-
-        # ==== 2.1 CREATE UI FOR ADVANCED OPTIONS ==== #
-        with st.beta_expander("Advanced options"):
-
-            steps_options = list(PreprocessingPipeline.pipeline_components().keys())
-
-            # stopwords option and
-            col1, col2 = st.beta_columns([1, 3])
-            with col1:
-                st.markdown("Remove stopwords (uses Spacy vocabulary)")
-            with col2:
-                remove_stopwords_elem = st.empty()
-
-            # lemmatization option
-            col1, col2 = st.beta_columns([1, 3])
-            with col1:
-                st.markdown("Lemmatizes text (uses Spacy)")
-            with col2:
-                lemmatization_elem = st.empty()
-
-            # pre-lemmatization cleaning steps and
-            # post-lemmatization cleaning steps
-            col1, col2 = st.beta_columns([1, 3])
-            with col1:
-                st.markdown(
-                    f"""
-                    Define a pipeline of cleaning steps that is applied before and/or after lemmatization.
-                    The available cleaning steps are:\n
-                    {", ".join([f"`{x.replace('_', ' ').title()}`" for x in steps_options])}
-                    """
-                )
-            with col2:
-                pre_steps_elem = st.empty()
-                post_steps_elem = st.empty()
-                reset_button = st.empty()
-
-            # implement reset logic
-            if reset_button.button("Reset steps"):
-                session.run_id += 1
-
-            pre_steps = pre_steps_elem.multiselect(
-                "Select pre-lemmatization preprocessing steps (ordered)",
-                options=steps_options,
-                default=steps_options,
-                format_func=lambda x: x.replace("_", " ").title(),
-                key=session.run_id,
-            )
-            post_steps = post_steps_elem.multiselect(
-                "Select post-lemmatization processing steps (ordered)",
-                options=steps_options,
-                default=steps_options[-4:],
-                format_func=lambda x: x.replace("_", " ").title(),
-                key=session.run_id,
-            )
-            remove_stopwords = remove_stopwords_elem.checkbox(
-                "Remove stopwords",
-                value=True,
-                key=session.run_id,
-            )
-            lemmatization = lemmatization_elem.checkbox(
-                "Lemmatize text",
-                value=True,
-                key=session.run_id,
-            )
-
-        # show sample checkbox
-        col1, col2 = st.beta_columns([1, 2])
-        with col1:
-            show_sample = st.checkbox("Show sample of preprocessed text")
-
-        # initialize text preprocessor
-        preprocessing_pipeline = PreprocessingPipeline(
-            pre_steps=pre_steps,
-            lemmatizer=Lemmatizer(
-                language=language,
-                remove_stop=remove_stopwords,
-                lemmatization=lemmatization,
-            ),
-            post_steps=post_steps,
-        )
-
-        print(preprocessing_pipeline.pre_steps)
-
-        # ==== 3. PROVIDE FEEDBACK ON OPTIONS ==== #
-        if show_sample and not (label_column and text_column):
-            st.warning("Please select `label` and `text` columns")
-
-        elif show_sample and (label_column and text_column):
-            sample_data = data.sample(5)
-            sample_data[f"preprocessed_{text_column}"] = preprocessing_pipeline(
-                sample_data[text_column]
-            ).values
-
-            print(sample_data)
-            st.table(
-                sample_data.loc[
-                    :, [label_column, text_column, f"preprocessed_{text_column}"]
-                ]
-            )
-
-        # ==== 4. RUN ==== #
-        run_button = st.button("Wordify!")
-        if run_button and not (label_column and text_column):
-            st.warning("Please select `label` and `text` columns")
-
-        elif run_button and (label_column and text_column) and not session.process:
-
-            with st.spinner("Process started"):
-                # data = data.head()
-                data[f"preprocessed_{text_column}"] = preprocessing_pipeline(
-                    data[text_column]
-                ).values
-
-                print(data.head())
-
-                inputs = encode(data[f"preprocessed_{text_column}"], data[label_column])
-                session.posdf, session.negdf = wordifier(**inputs)
-            st.success("Wordified!")
-
-            # session.posdf, session.negdf = process(data, text_column, label_column)
-            session.process = True
-
-        # ==== 5. RESULTS ==== #
-        if session.process and (label_column and text_column):
-            st.markdown("")
-            st.markdown("")
-            st.header("Results")
-
-            # col1, col2, _ = st.beta_columns(3)
-            col1, col2, col3 = st.beta_columns([2, 3, 3])
-
-            with col1:
-                label = st.selectbox(
-                    "Select label", data[label_column].unique().tolist()
-                )
-                # # with col2:
-                # thres = st.slider(
-                #     "Select threshold",
-                #     min_value=0,
-                #     max_value=100,
-                #     step=1,
-                #     format="%f",
-                #     value=30,
-                # )
-                show_plots = st.checkbox("Show plots of top 100")
-
-            with col2:
-                st.subheader(f"Words __positively__ identifying label `{label}`")
-                st.write(
-                    session.posdf[session.posdf[label_column] == label].sort_values(
-                        "score", ascending=False
-                    )
-                )
-                download_button(session.posdf, "positive_data")
-                if show_plots:
-                    st.altair_chart(
-                        plot_score(session.posdf, label_column, label),
-                        use_container_width=True,
-                    )
-
-            with col3:
-                st.subheader(f"Words __negatively__ identifying label `{label}`")
-                st.write(
-                    session.negdf[session.negdf[label_column] == label].sort_values(
-                        "score", ascending=False
-                    )
-                )
-                download_button(session.negdf, "negative_data")
-                if show_plots:
-                    st.altair_chart(
-                        plot_score(session.negdf, label_column, label),
-                        use_container_width=True,
-                    )

src/plotting.py

@@ -1,84 +0,0 @@
-import altair as alt
-import pandas as pd
-import streamlit as st
-from stqdm import stqdm
-
-stqdm.pandas()
-
-
-def plot_labels_prop(data: pd.DataFrame, label_column: str):
-
-    unique_value_limit = 100
-
-    if data[label_column].nunique() > unique_value_limit:
-
-        st.warning(
-            f"""
-            The column you selected has more than {unique_value_limit}.
-            Are you sure it's the right column? If it is, please note that
-            this will impact __Wordify__ performance.
-            """
-        )
-
-        return
-
-    source = (
-        data[label_column]
-        .value_counts()
-        .reset_index()
-        .rename(columns={"index": "Labels", label_column: "Counts"})
-    )
-    source["Props"] = source["Counts"] / source["Counts"].sum()
-    source["Proportions"] = (source["Props"].round(3) * 100).map("{:,.2f}".format) + "%"
-
-    bars = (
-        alt.Chart(source)
-        .mark_bar()
-        .encode(
-            x=alt.X("Labels:O", sort="-y"),
-            y="Counts:Q",
-        )
-    )
-
-    text = bars.mark_text(align="center", baseline="middle", dy=15).encode(
-        text="Proportions:O"
-    )
-
-    return (bars + text).properties(height=300)
-
-
-def plot_nchars(data: pd.DataFrame, text_column: str):
-    source = data[text_column].str.len().to_frame()
-
-    plot = (
-        alt.Chart(source)
-        .mark_bar()
-        .encode(
-            alt.X(
-                f"{text_column}:Q", bin=True, axis=alt.Axis(title="# chars per text")
-            ),
-            alt.Y("count()", axis=alt.Axis(title="")),
-        )
-    )
-
-    return plot.properties(height=300)
-
-
-def plot_score(data: pd.DataFrame, label_col: str, label: str):
-
-    source = (
-        data.loc[data[label_col] == label]
-        .sort_values("score", ascending=False)
-        .head(100)
-    )
-
-    plot = (
-        alt.Chart(source)
-        .mark_bar()
-        .encode(
-            y=alt.Y("word:O", sort="-x"),
-            x="score:Q",
-        )
-    )
-
-    return plot.properties(height=max(30 * source.shape[0], 50))

src/preprocessing.py

@@ -6,10 +6,10 @@ from collections import OrderedDict
 from typing import Callable, List, Optional
 
 import pandas as pd
-from pandas.core.frame import DataFrame
 import spacy
 import streamlit as st
 import vaex
+from pandas.core.frame import DataFrame
 from pandas.core.series import Series
 from textacy.preprocessing import make_pipeline, normalize, remove, replace
 
@@ -103,7 +103,9 @@ class PreprocessingPipeline:
             return self.post(self.lemma(self.nlp(self.pre(t))))
 
         vdf = vaex.from_pandas(df)
-        vdf["processed_text"] = vdf.apply(fn, arguments=[vdf[text_column]], vectorize=False)
+        vdf["processed_text"] = vdf.apply(
+            fn, arguments=[vdf[text_column]], vectorize=False
+        )
 
         return vdf.to_pandas_df()
 
@@ -115,7 +117,9 @@ class PreprocessingPipeline:
             total_steps = len(series) // 100
             res = []
             pbar = st.progress(0)
-            for i, doc in enumerate(self.nlp.pipe(series, batch_size=500, n_process=os.cpu_count())):
+            for i, doc in enumerate(
+                self.nlp.pipe(series, batch_size=500, n_process=os.cpu_count())
+            ):
                 res.append(self.lemma(doc))
 
                 if i % total_steps == 0:

src/session_state.py

@@ -1,121 +0,0 @@
-"""Hack to add per-session state to Streamlit.
-
-Usage
------
-
->>> import SessionState
->>>
->>> session_state = SessionState.get(user_name='', favorite_color='black')
->>> session_state.user_name
-''
->>> session_state.user_name = 'Mary'
->>> session_state.favorite_color
-'black'
-
-Since you set user_name above, next time your script runs this will be the
-result:
->>> session_state = get(user_name='', favorite_color='black')
->>> session_state.user_name
-'Mary'
-
-"""
-try:
-    import streamlit.ReportThread as ReportThread
-    from streamlit.server.Server import Server
-except Exception:
-    # Streamlit >= 0.65.0
-    import streamlit.report_thread as ReportThread
-    from streamlit.server.server import Server
-
-
-class SessionState(object):
-    def __init__(self, **kwargs):
-        """A new SessionState object.
-
-        Parameters
-        ----------
-        **kwargs : any
-            Default values for the session state.
-
-        Example
-        -------
-        >>> session_state = SessionState(user_name='', favorite_color='black')
-        >>> session_state.user_name = 'Mary'
-        ''
-        >>> session_state.favorite_color
-        'black'
-
-        """
-        for key, val in kwargs.items():
-            setattr(self, key, val)
-
-
-def get(**kwargs):
-    """Gets a SessionState object for the current session.
-
-    Creates a new object if necessary.
-
-    Parameters
-    ----------
-    **kwargs : any
-        Default values you want to add to the session state, if we're creating a
-        new one.
-
-    Example
-    -------
-    >>> session_state = get(user_name='', favorite_color='black')
-    >>> session_state.user_name
-    ''
-    >>> session_state.user_name = 'Mary'
-    >>> session_state.favorite_color
-    'black'
-
-    Since you set user_name above, next time your script runs this will be the
-    result:
-    >>> session_state = get(user_name='', favorite_color='black')
-    >>> session_state.user_name
-    'Mary'
-
-    """
-    # Hack to get the session object from Streamlit.
-
-    ctx = ReportThread.get_report_ctx()
-
-    this_session = None
-
-    current_server = Server.get_current()
-    if hasattr(current_server, "_session_infos"):
-        # Streamlit < 0.56
-        session_infos = Server.get_current()._session_infos.values()
-    else:
-        session_infos = Server.get_current()._session_info_by_id.values()
-
-    for session_info in session_infos:
-        s = session_info.session
-        if (
-            # Streamlit < 0.54.0
-            (hasattr(s, "_main_dg") and s._main_dg == ctx.main_dg)
-            or
-            # Streamlit >= 0.54.0
-            (not hasattr(s, "_main_dg") and s.enqueue == ctx.enqueue)
-            or
-            # Streamlit >= 0.65.2
-            (
-                not hasattr(s, "_main_dg")
-                and s._uploaded_file_mgr == ctx.uploaded_file_mgr
-            )
-        ):
-            this_session = s
-
-    if this_session is None:
-        raise RuntimeError(
-            "Oh noes. Couldn't get your Streamlit Session object. "
-            "Are you doing something fancy with threads?"
-        )
-
-    # Got the session object! Now let's attach some state into it.
-
-    if not hasattr(this_session, "_custom_session_state"):
-        this_session._custom_session_state = SessionState(**kwargs)
-
-    return this_session._custom_session_state

src/utils.py

@@ -1,4 +1,5 @@
 import base64
+
 import altair as alt
 import pandas as pd
 import streamlit as st
@@ -7,7 +8,6 @@ from PIL import Image
 from .configs import SupportedFiles
 
 
-
 @st.cache
 def get_logo(path):
     return Image.open(path)
@@ -52,7 +52,12 @@ def plot_labels_prop(data: pd.DataFrame, label_column: str):
 
         return
 
-    source = data[label_column].value_counts().reset_index().rename(columns={"index": "Labels", label_column: "Counts"})
+    source = (
+        data[label_column]
+        .value_counts()
+        .reset_index()
+        .rename(columns={"index": "Labels", label_column: "Counts"})
+    )
     source["Props"] = source["Counts"] / source["Counts"].sum()
     source["Proportions"] = (source["Props"].round(3) * 100).map("{:,.2f}".format) + "%"
 
@@ -65,7 +70,9 @@ def plot_labels_prop(data: pd.DataFrame, label_column: str):
         )
     )
 
-    text = bars.mark_text(align="center", baseline="middle", dy=15).encode(text="Proportions:O")
+    text = bars.mark_text(align="center", baseline="middle", dy=15).encode(
+        text="Proportions:O"
+    )
 
     return (bars + text).properties(height=300)
 
@@ -77,7 +84,9 @@ def plot_nchars(data: pd.DataFrame, text_column: str):
         alt.Chart(source)
         .mark_bar()
         .encode(
-            alt.X(f"{text_column}:Q", bin=True, axis=alt.Axis(title="# chars per text")),
+            alt.X(
+                f"{text_column}:Q", bin=True, axis=alt.Axis(title="# chars per text")
+            ),
             alt.Y("count()", axis=alt.Axis(title="")),
         )
     )
@@ -87,7 +96,11 @@ def plot_nchars(data: pd.DataFrame, text_column: str):
 
 def plot_score(data: pd.DataFrame, label_col: str, label: str):
 
-    source = data.loc[data[label_col] == label].sort_values("score", ascending=False).head(100)
+    source = (
+        data.loc[data[label_col] == label]
+        .sort_values("score", ascending=False)
+        .head(100)
+    )
 
     plot = (
         alt.Chart(source)

src/wordifier.py

@@ -12,7 +12,9 @@ from sklearn.utils import resample
 from .configs import InputTransformConfigs, ModelConfigs
 
 
-def input_transform(text: pd.Series, labels: pd.Series, configs=InputTransformConfigs) -> Dict[str, np.ndarray]:
+def input_transform(
+    text: pd.Series, labels: pd.Series, configs=InputTransformConfigs
+) -> Dict[str, np.ndarray]:
     """
     Encodes text in mathematical object ameanable to training algorithm
     """
@@ -45,7 +47,11 @@ def input_transform(text: pd.Series, labels: pd.Series, configs=InputTransformCo
 
 
 def wordifier(
-    X: np.ndarray, y: np.ndarray, X_names: List[str], y_names: List[str], configs=ModelConfigs
+    X: np.ndarray,
+    y: np.ndarray,
+    X_names: List[str],
+    y_names: List[str],
+    configs=ModelConfigs,
 ) -> List[Tuple[str, float, str]]:
 
     n_instances, n_features = X.shape
@@ -85,7 +91,9 @@ def wordifier(
         )
 
         # sample indices to subsample matrix
-        selection = resample(np.arange(n_instances), replace=True, stratify=y, n_samples=sample_size)
+        selection = resample(
+            np.arange(n_instances), replace=True, stratify=y, n_samples=sample_size
+        )
 
         # fit
         try:
@@ -110,20 +118,36 @@ def wordifier(
     neg_scores = neg_scores / configs.NUM_ITERS.value
 
     # get only active features
-    pos_positions = np.where(pos_scores >= configs.SELECTION_THRESHOLD.value, pos_scores, 0)
-    neg_positions = np.where(neg_scores >= configs.SELECTION_THRESHOLD.value, neg_scores, 0)
+    pos_positions = np.where(
+        pos_scores >= configs.SELECTION_THRESHOLD.value, pos_scores, 0
+    )
+    neg_positions = np.where(
+        neg_scores >= configs.SELECTION_THRESHOLD.value, neg_scores, 0
+    )
 
     # prepare DataFrame
-    pos = [(X_names[i], pos_scores[c, i], y_names[c]) for c, i in zip(*pos_positions.nonzero())]
-    neg = [(X_names[i], neg_scores[c, i], y_names[c]) for c, i in zip(*neg_positions.nonzero())]
+    pos = [
+        (X_names[i], pos_scores[c, i], y_names[c])
+        for c, i in zip(*pos_positions.nonzero())
+    ]
+    neg = [
+        (X_names[i], neg_scores[c, i], y_names[c])
+        for c, i in zip(*neg_positions.nonzero())
+    ]
 
     return pos, neg
 
 
-def output_transform(pos: List[Tuple[str, float, str]], neg: List[Tuple[str, float, str]]) -> DataFrame:
-    posdf = pd.DataFrame(pos, columns="word score label".split()).sort_values(["label", "score"], ascending=False)
+def output_transform(
+    pos: List[Tuple[str, float, str]], neg: List[Tuple[str, float, str]]
+) -> DataFrame:
+    posdf = pd.DataFrame(pos, columns="word score label".split()).sort_values(
+        ["label", "score"], ascending=False
+    )
     posdf["correlation"] = "positive"
-    negdf = pd.DataFrame(neg, columns="word score label".split()).sort_values(["label", "score"], ascending=False)
+    negdf = pd.DataFrame(neg, columns="word score label".split()).sort_values(
+        ["label", "score"], ascending=False
+    )
     negdf["correlation"] = "negative"
 
     output = pd.concat([posdf, negdf], ignore_index=False, axis=0)