add: app.py

app.py

@@ -0,0 +1,157 @@
+import streamlit as st
+from transformers import pipeline
+
+############ SETTING UP THE PAGE LAYOUT AND TITLE ############
+
+# `st.set_page_config` is used to display the default layout width, the title of the app, and the emoticon in the browser tab.
+
+st.set_page_config(layout="centered", page_title="X_G85 Fake News", page_icon="📑")
+
+############ CREATE THE LOGO AND HEADING ############
+
+# We create a set of columns to display the logo and the heading next to each other.
+
+c1, c2 = st.columns([0.32, 2])
+
+# The snowflake logo will be displayed in the first column, on the left.
+
+with c1:
+    st.caption("")
+    st.title("📑")
+
+# The heading will be on the right.
+
+with c2:
+
+  st.caption("")
+  st.title("X_G85 Fake News")
+
+# We need to set up session state via st.session_state so that app interactions don't reset the app.
+
+############ SIDEBAR CONTENT ############
+
+st.sidebar.subheader("Model Options")
+st.sidebar.write("")
+
+
+# Model selection
+SELECTED_MODEL = st.sidebar.selectbox(
+    "Choose a model",
+    ("Bert", "Roberta", "Lstm")
+)
+
+MODEL_INFO = {
+    "Bert":  """
+    #### [BERT base model (uncased)](https://huggingface.co/google-bert/bert-base-uncased)
+    Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased: it does not make a difference between english and English.
+    """,
+
+    "Roberta":  """
+    #### [jy46604790/Fake-News-Bert-Detect](https://huggingface.co/jy46604790/Fake-News-Bert-Detect)
+    This model is trained by over 40,000 news from different medias based on the 'roberta-base'. It can give result by simply entering the text of the news less than 500 words(the excess will be truncated automatically).
+    """,
+
+    "Lstm":  """
+    #### [X_G85 Fake News LSTM MODEL](https://huggingface.co/x-g85)
+    It is trained on the provided datasets\n
+    Notebook: [Fake News using Lstm](https://www.kaggle.com/code/adamalrahman/fake-news-using-lstm)
+    """,
+    None: "NO MODEL SELECTED"
+}
+
+
+
+model_info_container = st.sidebar.container(border=True)
+model_info_container.markdown("### Model Information\n")
+model_info_container.markdown(MODEL_INFO[SELECTED_MODEL ])
+
+
+copyright_container = st.sidebar.container(border=True)
+copyright_container.markdown("Copyright ©️ 2024 [X_G85](https://huggingface.co/x-g85)")
+
+
+############ TABBED NAVIGATION ############
+
+
+MainTab, InfoTab = st.tabs(["Main", "Info"])
+
+with InfoTab:
+
+    st.subheader("X_G85 Fake News")
+    st.markdown("It is fake news detection based on the following models trained on datasets")
+
+    st.subheader("Datasets")
+    st.markdown(
+        """
+        We have used following datasets to create our own datasets and train models.
+        - [Kaggle: Fake news detection dataset english](https://www.kaggle.com/datasets/sadikaljarif/fake-news-detection-dataset-english)
+        - [Kaggle: Liar twitter](https://www.kaggle.com/datasets/muhammadimran112233/liar-twitter-dataset)
+        - [Kaggle: Liar Preprocessed](https://www.kaggle.com/datasets/khandalaryan/liar-preprocessed-dataset)
+        - [Kaggle: Stocknews](https://www.kaggle.com/datasets/aaron7sun/stocknews)
+        """
+    )
+
+    st.subheader("Credits")
+    st.markdown(
+        """
+        - Bert: [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) 
+        - Roberta: [jy46604790/Fake-News-Bert-Detect](https://huggingface.co/jy46604790/Fake-News-Bert-Detect)
+        """)
+    st.write("")
+    copyright_container = st.container(border=True)
+    copyright_container.markdown("Copyright ©️ 2024 [X_G85](https://huggingface.co/x-g85)")
+
+
+
+def MODEL_RESULT(model: str, news: str) -> str | None:
+    if model == "Roberta":
+        MODEL_jy46604790 = "jy46604790/Fake-News-Bert-Detect"
+        classifier = pipeline("text-classification", model=MODEL_jy46604790, tokenizer=MODEL_jy46604790)
+        result = classifier(news)
+       
+        if result[0]["label"] == "LABEL_1":
+            return "Real NEWS"
+        else: 
+            return "FAKE NEWS"
+    
+    # TODO(Adam-Al-Rahman): Complete the statement
+    if model == "Bert":
+        pass
+
+    if model == "Lstm":
+        pass
+
+
+
+with MainTab:
+
+    # Then, we create a intro text for the app, which we wrap in a st.markdown() widget.
+
+    st.write("")
+    st.markdown("Classify News based on the selected ml model.")
+    st.write("")
+    container = st.container(border=True)
+    container.write(f"Selected model: {SELECTED_MODEL}")
+
+
+    # --------------------
+
+    news = st.text_area("Enter News",
+                        height=200,
+                        help="Please provide the news that you need to verify for its truthfulness.\n Press Ctrl+Enter to apply",
+                        key="news")
+
+    # Default Model: Bert
+    result = MODEL_RESULT(model=SELECTED_MODEL if SELECTED_MODEL else "Bert", news=news)
+    result_container = st.container(border=True)
+    if news:
+        if result:
+            result_container.markdown(f"Result: {result}")
+        else:
+            result_container.markdown("ML MODEL ERROR")
+
+
+
+
+
+

setup.cfg

@@ -0,0 +1,69 @@
+# Project-wide configuration file, can be used for package metadata and other toll configurations
+# Example usage: global configuration for PEP8 (via flake8) setting or default pytest arguments
+# Local usage: pip install pre-commit, pre-commit run --all-files
+
+[metadata]
+license_files = LICENSE
+description_file = README.md
+
+[tool:pytest]
+norecursedirs =
+    .git
+    dist
+    build
+addopts =
+    --doctest-modules
+    --durations=30
+    --color=yes
+
+[flake8]
+ignore = E266
+max-line-length = 120
+exclude = .tox,*.egg,build,temp
+indent-size = 2
+select = E,W,F
+doctests = True
+verbose = 2
+# https://pep8.readthedocs.io/en/latest/intro.html#error-codes
+format = pylint
+# see: https://www.flake8rules.com/
+ignore = E731,F405,E402,W504,E501
+    # E731: Do not assign a lambda expression, use a def
+    # F405: name may be undefined, or defined from star imports: module
+    # E402: module level import not at top of file
+    # W504: line break after binary operator
+    # E501: line too long
+    # removed:
+    # F401: module imported but unused
+    # E231: missing whitespace after ‘,’, ‘;’, or ‘:’
+    # E127: continuation line over-indented for visual indent
+
+
+
+[isort]
+# https://pycqa.github.io/isort/docs/configuration/options.html
+line_length = 120
+# see: https://pycqa.github.io/isort/docs/configuration/multi_line_output_modes.html
+multi_line_output = 0
+
+[yapf]
+based_on_style = google
+spaces_before_comment = 2
+indent_width = 2
+CONTINUATION_INDENT_WIDTH = 2
+COLUMN_LIMIT = 120
+COALESCE_BRACKETS = True
+SPACES_AROUND_POWER_OPERATOR = True
+SPACE_BETWEEN_ENDING_COMMA_AND_CLOSING_BRACKET = True
+SPLIT_BEFORE_CLOSING_BRACKET = False
+SPLIT_BEFORE_FIRST_ARGUMENT = False
+# EACH_DICT_ENTRY_ON_SEPARATE_LINE = False
+
+[docformatter]
+wrap-summaries = 120
+wrap-descriptions = 120
+in-place = true
+make-summary-multi-line = false
+pre-summary-newline = true
+force-wrap = false
+close-quotes-on-newline = true