Spaces:
Sleeping
Sleeping
| """Streamlit app for Presidio.""" | |
| import logging | |
| import os | |
| import traceback | |
| import dotenv | |
| import pandas as pd | |
| import streamlit as st | |
| import streamlit.components.v1 as components | |
| from annotated_text import annotated_text | |
| from streamlit_tags import st_tags | |
| # from openai_fake_data_generator import OpenAIParams | |
| from presidio_helpers import ( | |
| get_supported_entities, | |
| analyze, | |
| anonymize, | |
| annotate, | |
| # create_fake_data, | |
| analyzer_engine, | |
| ) | |
| st.set_page_config( | |
| page_title="Presidio demo", | |
| layout="wide", | |
| initial_sidebar_state="expanded", | |
| # menu_items={ | |
| # "About": "https://microsoft.github.io/presidio/", | |
| # }, | |
| ) | |
| dotenv.load_dotenv() | |
| logger = logging.getLogger("presidio-streamlit") | |
| allow_other_models = os.getenv("ALLOW_OTHER_MODELS", False) | |
| # Sidebar | |
| st.sidebar.header( | |
| """ | |
| Personal Info Anonymization | |
| """ | |
| ) | |
| # set aliae logo | |
| st.sidebar.image('logo.png', use_column_width=True) | |
| model_help_text = """ | |
| Select which Named Entity Recognition (NER) model to use for PII detection, in parallel to rule-based recognizers. | |
| Presidio supports multiple NER packages off-the-shelf, such as spaCy, Huggingface, Stanza and Flair, | |
| as well as service such as Azure Text Analytics PII. | |
| """ | |
| st_ta_key = st_ta_endpoint = "" | |
| model_list = [ | |
| "spaCy/en_core_web_lg", | |
| "spaCy/fr_core_news_md", | |
| ] | |
| # "flair/ner-english-large", | |
| # | |
| # "HuggingFace/StanfordAIMI/stanford-deidentifier-base", | |
| # "Azure Text Analytics PII", | |
| # "Other", | |
| # if not allow_other_models: | |
| # model_list.pop() | |
| # Select model | |
| lang = st.sidebar.selectbox( | |
| "Language", | |
| ['en','fr'], | |
| index=0, | |
| ) | |
| # Extract model package. | |
| # st_model_package = st_model.split("/")[0] | |
| st_model_package = 'spaCy' | |
| # # Remove package prefix (if needed) | |
| # st_model = ( | |
| # st_model | |
| # if st_model_package not in ("spaCy", "HuggingFace") | |
| # else "/".join(st_model.split("/")[1:]) | |
| # ) | |
| st_model = 'en_core_web_lg' | |
| if lang =='en': st_model = 'en_core_web_lg' | |
| elif lang == 'fr' : st_model = 'fr_core_news_md' | |
| # if st_model == "Other": | |
| # st_model_package = st.sidebar.selectbox( | |
| # "NER model OSS package", options=["spaCy", "Flair", "HuggingFace"] | |
| # ) | |
| # st_model = st.sidebar.text_input(f"NER model name", value="") | |
| # if st_model == "Azure Text Analytics PII": | |
| # st_ta_key = st.sidebar.text_input( | |
| # f"Text Analytics key", value=os.getenv("TA_KEY", ""), type="password" | |
| # ) | |
| # st_ta_endpoint = st.sidebar.text_input( | |
| # f"Text Analytics endpoint", | |
| # value=os.getenv("TA_ENDPOINT", default=""), | |
| # help="For more info: https://learn.microsoft.com/en-us/azure/cognitive-services/language-service/personally-identifiable-information/overview", # noqa: E501 | |
| # ) | |
| # st.sidebar.warning("Note: Models might take some time to download. ") | |
| analyzer_params = (st_model_package, st_model, st_ta_key, st_ta_endpoint) | |
| logger.debug(f"analyzer_params: {analyzer_params}") | |
| st_operator = st.sidebar.selectbox( | |
| "De-identification approach", | |
| ["redact", "replace", "highlight"], | |
| index=2, | |
| help=""" | |
| Select which manipulation to the text is requested after PII has been identified.\n | |
| - Redact: Completely remove the PII text\n | |
| - Replace: Replace the PII text with a constant, e.g. <PERSON>\n | |
| - Highlight: Shows the original text with PII highlighted in colors\n | |
| """, | |
| ) | |
| st_mask_char = "*" | |
| st_number_of_chars = 15 | |
| st_encrypt_key = "WmZq4t7w!z%C&F)J" | |
| open_ai_params = None | |
| logger.debug(f"st_operator: {st_operator}") | |
| # if st_operator == "mask": | |
| # st_number_of_chars = st.sidebar.number_input( | |
| # "number of chars", value=st_number_of_chars, min_value=0, max_value=100 | |
| # ) | |
| # st_mask_char = st.sidebar.text_input( | |
| # "Mask character", value=st_mask_char, max_chars=1 | |
| # ) | |
| # elif st_operator == "encrypt": | |
| # st_encrypt_key = st.sidebar.text_input("AES key", value=st_encrypt_key) | |
| # elif st_operator == "synthesize": | |
| # if os.getenv("OPENAI_TYPE", default="openai") == "Azure": | |
| # openai_api_type = "azure" | |
| # st_openai_api_base = st.sidebar.text_input( | |
| # "Azure OpenAI base URL", | |
| # value=os.getenv("AZURE_OPENAI_ENDPOINT", default=""), | |
| # ) | |
| # st_deployment_name = st.sidebar.text_input( | |
| # "Deployment name", value=os.getenv("AZURE_OPENAI_DEPLOYMENT", default="") | |
| # ) | |
| # st_openai_version = st.sidebar.text_input( | |
| # "OpenAI version", | |
| # value=os.getenv("OPENAI_API_VERSION", default="2023-05-15"), | |
| # ) | |
| # else: | |
| # st_openai_version = openai_api_type = st_openai_api_base = None | |
| # st_deployment_name = "" | |
| # st_openai_key = st.sidebar.text_input( | |
| # "OPENAI_KEY", | |
| # value=os.getenv("OPENAI_KEY", default=""), | |
| # help="See https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key for more info.", | |
| # type="password", | |
| # ) | |
| # st_openai_model = st.sidebar.text_input( | |
| # "OpenAI model for text synthesis", | |
| # value=os.getenv("OPENAI_MODEL", default="text-davinci-003"), | |
| # help="See more here: https://platform.openai.com/docs/models/", | |
| # ) | |
| # | |
| # open_ai_params = OpenAIParams( | |
| # openai_key=st_openai_key, | |
| # model=st_openai_model, | |
| # api_base=st_openai_api_base, | |
| # deployment_name=st_deployment_name, | |
| # api_version=st_openai_version, | |
| # api_type=openai_api_type, | |
| # ) | |
| # st_threshold = st.sidebar.slider( | |
| # label="Acceptance threshold", | |
| # min_value=0.0, | |
| # max_value=1.0, | |
| # value=0.35, | |
| # help="Define the threshold for accepting a detection as PII. See more here: ", | |
| # ) | |
| st_threshold = 0.35 | |
| # | |
| # st_return_decision_process = st.sidebar.checkbox( | |
| # "Add analysis explanations to findings", | |
| # value=False, | |
| # help="Add the decision process to the output table. " | |
| # "More information can be found here: https://microsoft.github.io/presidio/analyzer/decision_process/", | |
| # ) | |
| st_return_decision_process = False | |
| # # Allow and deny lists | |
| # st_deny_allow_expander = st.sidebar.expander( | |
| # "Allowlists and denylists", | |
| # expanded=False, | |
| # ) | |
| # | |
| # with st_deny_allow_expander: | |
| # st_allow_list = st_tags( | |
| # label="Add words to the allowlist", text="Enter word and press enter." | |
| # ) | |
| # st.caption( | |
| # "Allowlists contain words that are not considered PII, but are detected as such." | |
| # ) | |
| # | |
| # st_deny_list = st_tags( | |
| # label="Add words to the denylist", text="Enter word and press enter." | |
| # ) | |
| # st.caption( | |
| # "Denylists contain words that are considered PII, but are not detected as such." | |
| # ) | |
| st_allow_list = [] | |
| st_deny_list = [] | |
| # Main panel | |
| with st.expander("About Microsoft Presidio", expanded=False): | |
| st.info( | |
| """Presidio is an open source customizable framework for PII detection and de-identification.""" | |
| ) | |
| analyzer_load_state = st.info("Starting Presidio analyzer...") | |
| analyzer_load_state.empty() | |
| # Read default text | |
| with open("en_demo_text.txt") as f: | |
| en_demo_text = f.readlines() | |
| with open("fr_demo_text.txt") as f: | |
| fr_demo_text = f.readlines() | |
| if lang == 'en': demo_text = en_demo_text | |
| elif lang == 'fr': demo_text = fr_demo_text | |
| # Create two columns for before and after | |
| col1, col2 = st.columns(2) | |
| # Before: | |
| col1.subheader("Input") | |
| st_text = col1.text_area( | |
| label="Enter text", value="".join(demo_text), height=400, key="text_input" | |
| ) | |
| try: | |
| # Choose entities | |
| st_entities_expander = st.sidebar.expander("Choose entities to look for") | |
| st_entities = st_entities_expander.multiselect( | |
| label="Which entities to look for?", | |
| options=get_supported_entities(*analyzer_params), | |
| default=list(get_supported_entities(*analyzer_params)), | |
| help="Limit the list of PII entities detected. " | |
| "This list is dynamic and based on the NER model and registered recognizers. " | |
| "More information can be found here: https://microsoft.github.io/presidio/analyzer/adding_recognizers/", | |
| ) | |
| # Before | |
| analyzer_load_state = st.info("Starting Presidio analyzer...") | |
| analyzer = analyzer_engine(*analyzer_params) | |
| analyzer_load_state.empty() | |
| st_analyze_results = analyze( | |
| *analyzer_params, | |
| text=st_text, | |
| entities=st_entities, | |
| language=lang, | |
| score_threshold=st_threshold, | |
| return_decision_process=st_return_decision_process, | |
| allow_list=st_allow_list, | |
| deny_list=st_deny_list, | |
| ) | |
| # After | |
| if st_operator not in ("highlight", "synthesize"): | |
| with col2: | |
| st.subheader(f"Output") | |
| st_anonymize_results = anonymize( | |
| text=st_text, | |
| operator=st_operator, | |
| mask_char=st_mask_char, | |
| number_of_chars=st_number_of_chars, | |
| encrypt_key=st_encrypt_key, | |
| analyze_results=st_analyze_results, | |
| ) | |
| st.text_area( | |
| label="De-identified", value=st_anonymize_results.text, height=400 | |
| ) | |
| # elif st_operator == "synthesize": | |
| # with col2: | |
| # st.subheader(f"OpenAI Generated output") | |
| # fake_data = create_fake_data( | |
| # st_text, | |
| # st_analyze_results, | |
| # open_ai_params, | |
| # ) | |
| # st.text_area(label="Synthetic data", value=fake_data, height=400) | |
| else: | |
| st.subheader("Highlighted") | |
| annotated_tokens = annotate(text=st_text, analyze_results=st_analyze_results) | |
| # annotated_tokens | |
| annotated_text(*annotated_tokens) | |
| # table result | |
| st.subheader( | |
| "Findings" | |
| if not st_return_decision_process | |
| else "Findings with decision factors" | |
| ) | |
| if st_analyze_results: | |
| df = pd.DataFrame.from_records([r.to_dict() for r in st_analyze_results]) | |
| df["text"] = [st_text[res.start : res.end] for res in st_analyze_results] | |
| df_subset = df[["entity_type", "text", "start", "end", "score"]].rename( | |
| { | |
| "entity_type": "Entity type", | |
| "text": "Text", | |
| "start": "Start", | |
| "end": "End", | |
| "score": "Confidence", | |
| }, | |
| axis=1, | |
| ) | |
| df_subset["Text"] = [st_text[res.start : res.end] for res in st_analyze_results] | |
| if st_return_decision_process: | |
| analysis_explanation_df = pd.DataFrame.from_records( | |
| [r.analysis_explanation.to_dict() for r in st_analyze_results] | |
| ) | |
| df_subset = pd.concat([df_subset, analysis_explanation_df], axis=1) | |
| st.dataframe(df_subset.reset_index(drop=True), use_container_width=True) | |
| else: | |
| st.text("No findings") | |
| except Exception as e: | |
| print(e) | |
| traceback.print_exc() | |
| st.error(e) | |
| components.html( | |
| """ | |
| <script type="text/javascript"> | |
| (function(c,l,a,r,i,t,y){ | |
| c[a]=c[a]||function(){(c[a].q=c[a].q||[]).push(arguments)}; | |
| t=l.createElement(r);t.async=1;t.src="https://www.clarity.ms/tag/"+i; | |
| y=l.getElementsByTagName(r)[0];y.parentNode.insertBefore(t,y); | |
| })(window, document, "clarity", "script", "h7f8bp42n8"); | |
| </script> | |
| """ | |
| ) | |