get some swaaaag

.gitignore

@@ -0,0 +1,2 @@
+venv
+.venv

.streamlit/config.toml

@@ -0,0 +1,9 @@
+[client]
+showErrorDetails = false
+
+[theme]
+primaryColor="#70a99f"
+backgroundColor="#212c2a"
+secondaryBackgroundColor="#415854"
+textColor="#70a99f"
+font="monospace"

app.py

@@ -4,21 +4,61 @@ from typing import Dict, List
 
 import plotly.express as px
 import streamlit as st
+import pandas as pd
 
 from datasets import Dataset, get_dataset_infos, load_dataset
+import stanza
+
+import matplotlib.pyplot as plt
+from wordcloud import WordCloud
+import io
+
+st.set_page_config(
+    page_title="Eskulap Dataset",
+    page_icon="🩺",
+    layout="wide",
+    initial_sidebar_state="expanded",
+)
+
 
 BASE_DATASET: str = "lion-ai/pl_med_data"
 read_key = os.environ.get('HF_TOKEN', None)
 
-
-dataset_names_map: Dict[str, str] = {
-    "znany_lekarz": "Porady - pytania i odpowiedzi",
-    "kor_epikryzy_qa": "Dokumentacja medyczna - pytania i odpowiedzi",
-    "wikipedia": "Ogólna wiedza medyczna - pytania i opowiedzi",
+datasets_map = {
+    "znany_lekarz":
+    {
+        "display_name": "Porady",
+        "description": "Zbiór pytań i odpowiedzi odnośnie medycyny.",
+        "primary_column": "question",
+    },
+    "kor_epikryzy_qa":
+    {
+        "display_name": "Dokumentacja - QA",
+        "description": "Zbiór pytań i odpowiedzi do zanonimizowanej dokumentacji medycznej.",
+        "primary_column": "content",
+    },
+    "wikipedia":
+    {
+        "display_name": "Wikipedia",
+        "description": "Zbiór pytań i odpowiedzi na podstawie artykułów z Wikipedii.",
+        "primary_column": "question",
+    },
+    "ulotki_medyczne":
+    {
+        "display_name": "Pytania farmaceutyczne",
+        "description": "Zbiór pytań i odpowiedzi na podstawie ulotek medycznych.",
+        "primary_column": "question",
+    },
 }
 
+
+dataset_names_map: Dict[str, str] = {k: v["display_name"] for k, v in datasets_map.items()}
+
 reverse_dataset_names_map: Dict[str, str] = {v: k for k, v in dataset_names_map.items()}
 
+@st.cache_resource
+def load_stanza_pipeline():
+    return stanza.Pipeline(lang='pl', processors='tokenize,mwt,pos,lemma')
 
 @st.cache_resource
 def list_datasets() -> Dict[str, Dataset]:
@@ -34,8 +74,8 @@ def list_datasets() -> Dict[str, Dataset]:
 def show_examples(dataset_name: str, split: str) -> None:
     dataset_name = reverse_dataset_names_map.get(dataset_name, dataset_name)
 
-    dataset: Dataset = load_dataset(BASE_DATASET, dataset_name, split=f"{split}[:10]", token=read_key)
-    st.data_editor(dataset.to_pandas(), use_container_width=True)
+    dataset: Dataset = load_dataset(BASE_DATASET, dataset_name, split=f"{split}[:50]", token=read_key)
+    st.data_editor(dataset.to_pandas(), use_container_width=True, height=900)
 
 
 def count_all_examples(datasets: Dict[str, Dataset]) -> None:
@@ -64,32 +104,101 @@ def filter_splits(dataset: Dict[str, Dataset], split: str) -> Dict[str, Dataset]
             dataset_splits[dataset_name] = dataset_info.splits[split]
     return dataset_splits
 
+@st.cache_data(show_spinner=False)
+def generate_wordcloud(dataset_name, split):
+    dataset_name = reverse_dataset_names_map.get(dataset_name, dataset_name)
 
-split: str = st.selectbox("splits", ["raw", "processed"])
-
-datasets: Dict[str, Dataset] = list_datasets()
-# st.write(datasets)
-
-filtered_datasets: Dict[str, Dataset] = filter_splits(datasets, split)
-# st.write(filtered_datasets)
-
-count_all_examples(filtered_datasets)
-
-# Create a pie chart showing the number of examples per dataset
-fig = px.pie(
-    values=[split.num_examples for split in filtered_datasets.values()],
-    names=list(filtered_datasets.keys()),
-    # title=f"Number of Examples per Dataset ({split} split)",
-    labels={"label": "Dataset", "value": "Number of Examples"},
-)
-
-# Update layout for better readability
-fig.update_traces(textposition="inside", textinfo="value+label")
-fig.update_layout(legend_title_text="Datasets", uniformtext_minsize=12, uniformtext_mode="hide")
-
-chart = st.plotly_chart(fig, use_container_width=True)
-
-
-dataset_name = st.selectbox("Select a dataset", list(filtered_datasets.keys()))
+    dataset: Dataset = load_dataset(BASE_DATASET, dataset_name, split=f"{split}[:500]", token=read_key)
+    
+    primary_column = datasets_map[dataset_name]["primary_column"]
+    
+    text = ""
+    progress_bar = st.progress(0, text = "Generating wordcloud...")
+    for i, example in enumerate(dataset[primary_column]):
+        doc = stanza_pipeline(example)
+        nouns = [word.lemma for sent in doc.sentences for word in sent.words if word.upos == 'NOUN']
+        text += " ".join(nouns) + " "
+        progress_bar.progress((i + 1) / len(dataset[primary_column]), text = f"Generating wordcloud...")
+    
+    wordcloud = WordCloud(width=600, height=600, background_color='#212c2a', colormap="Greens", contour_width=0, contour_color="#212c2a").generate(text)
+    progress_bar.empty()
+    
+    plt.figure(figsize=(6, 6), facecolor='#212c2a')
+    plt.imshow(wordcloud, interpolation='bilinear')
+    plt.axis('off')
+    plt.tight_layout(pad=0)
+    
+    # Save the plot to a bytes buffer
+    buf = io.BytesIO()
+    plt.savefig(buf, format='png', bbox_inches='tight', pad_inches=0, facecolor='#212c2a')
+    buf.seek(0)
+    
+    # Display the image in Streamlit
+    st.image(buf, use_column_width=True)
+
+
+_, col, _ = st.columns([1, 2, 1])
+
+with col:
+    split: str = "processed"
+
+    datasets: Dict[str, Dataset] = list_datasets()
+    stanza_pipeline = load_stanza_pipeline()
+    # st.write(datasets)
+
+    filtered_datasets: Dict[str, Dataset] = filter_splits(datasets, split)
+    # st.write(filtered_datasets)
+    image = st.image("Eskulap.png", use_column_width=True)
+
+    count_all_examples(filtered_datasets)
+
+    distribution = {
+        "dataset": list(filtered_datasets.keys()),
+        "count": [split.num_examples for split in filtered_datasets.values()],
+    }
+
+    distribution_df = pd.DataFrame(distribution)
+
+    # Create a pie chart showing the number of examples per dataset
+    fig = px.pie(
+        distribution_df,
+        names="dataset",
+        values="count",
+        hover_name="dataset",
+        title=f"Data distribution",
+        labels={"label": "Dataset", "value": "Number of Examples"},
+        color_discrete_sequence=px.colors.sequential.Blugrn,
+        hole=0.3,
+    )
+
+    # Update layout for better readability
+    # fig.update_traces(textposition="inside", textinfo="value+label")
+    fig.update_traces(textposition='none')
+    fig.update_layout(legend_title_text="Datasets", uniformtext_minsize=12, uniformtext_mode="hide")
+
+    chart = st.plotly_chart(fig, use_container_width=True)
+
+
+    dataset_name = st.selectbox("Select a dataset", list(filtered_datasets.keys()))
+    st.write(f"### {dataset_name}")
+    st.write(datasets_map[reverse_dataset_names_map.get(dataset_name)]["description"])
+st.markdown("***")
+col1, col2 = st.columns(2)
+with col1:
+    st.write(f"### Sample data")
+    show_examples(dataset_name, split)
+
+
+with col2:
+    st.write(f"### Wordcloud")
+    generate_wordcloud(dataset_name, split)
+
+_, col, _ = st.columns([1, 2, 1])
+
+
+with col:
+    st.button("Made with ❤️ by thelion.ai", use_container_width=True, disabled=True)
+    st.write("Intersted in the project? Contact us : contact@thelion.ai")
+
+    
 
-show_examples(dataset_name, split)

requirements.txt

@@ -1 +1,3 @@
-plotly==5.23.0
+plotly==5.23.0
+wordcloud==1.9.3
+stanze==1.8.2