Upload 6 files

.devcontainer/devcontainer.json

@@ -0,0 +1,33 @@
+{
+  "name": "Python 3",
+  // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+  "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
+  "customizations": {
+    "codespaces": {
+      "openFiles": [
+        "README.md",
+        "Movie_Reviews.py"
+      ]
+    },
+    "vscode": {
+      "settings": {},
+      "extensions": [
+        "ms-python.python",
+        "ms-python.vscode-pylance"
+      ]
+    }
+  },
+  "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
+  "postAttachCommand": {
+    "server": "streamlit run Movie_Reviews.py --server.enableCORS false --server.enableXsrfProtection false"
+  },
+  "portsAttributes": {
+    "8501": {
+      "label": "Application",
+      "onAutoForward": "openPreview"
+    }
+  },
+  "forwardPorts": [
+    8501
+  ]
+}

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Movie_Reviews.py

@@ -0,0 +1,68 @@
+import streamlit as st
+
+st.set_page_config(page_title="Turkish Review Analysis - via AG", page_icon='📖')
+st.header("📖Movie Review Analysis - TR")
+
+with st.sidebar:
+    hf_key = st.text_input("HuggingFace Access Key", key="hf_key", type="password")
+
+MODEL_MOVIE = {
+    "albert": "anilguven/albert_tr_turkish_movie_reviews",  # Add the emoji for the Meta-Llama model
+    "distilbert": "anilguven/distilbert_tr_turkish_movie_reviews",
+    "bert": "anilguven/bert_tr_turkish_movie_reviews",
+    "electra": "anilguven/electra_tr_turkish_movie_reviews",
+}
+
+MODEL_MOVIES = ["albert","distilbert","bert","electra"]
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+# Create a mapping from formatted model names to their original identifiers
+def format_model_name(model_key):
+    name_parts = model_key
+    formatted_name = ''.join(name_parts)  # Join them into a single string with title case
+    return formatted_name
+
+formatted_names_to_identifiers = {
+    format_model_name(key): key for key in MODEL_MOVIE.keys()
+}
+
+with st.expander("About this app"):
+    st.write(f"""
+    1-Choose your model for movie review analysis (negative or positive).\n
+    2-Enter your sample text.\n
+    3-And model predict your text's result. 
+    """)
+    
+# Debug to ensure names are formatted correctly
+#st.write("Formatted Model Names to Identifiers:", formatted_names_to_identifiers)
+
+model_name: str = st.selectbox("Model", options=MODEL_MOVIES)
+selected_model = MODEL_MOVIE[model_name]
+
+if not hf_key:
+    st.info("Please add your HuggingFace Access Key to continue.")
+    st.stop()
+
+access_token = hf_key
+pipe = pipeline("text-classification", model=selected_model, token=access_token)
+
+#from transformers import AutoTokenizer, AutoModelForSequenceClassification
+#tokenizer = AutoTokenizer.from_pretrained(selected_model)
+#pipe = AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path=selected_model)
+
+comment = st.text_input("Enter your text for analysis")#User input
+
+st.text('')
+if st.button("Submit for Analysis"):#User Review Button
+    if not hf_key:
+        st.info("Please add your HuggingFace Access Key to continue.")
+        st.stop()
+    else:
+        result = pipe(comment)[0]
+        label=''
+        if result["label"] == "LABEL_0": label = "Negative"
+        else: label = "Positive"
+        st.text(label + " comment with " + str(result["score"]) + " accuracy")
+
+

pages/1_Hotel_Reviews.py

@@ -0,0 +1,73 @@
+import streamlit as st
+
+st.set_page_config(page_title="Turkish Review Analysis - via AG", page_icon='📖')
+st.header("📖Hotel Review Analysis - TR")
+
+with st.sidebar:
+    hf_key = st.text_input("HuggingFace Access Key", key="hf_key", type="password")
+
+MODEL_HOTEL = {
+    "albert": "anilguven/albert_tr_turkish_hotel_reviews",  # Add the emoji for the Meta-Llama model
+    "distilbert": "anilguven/distilbert_tr_turkish_hotel_reviews",
+    "bert": "anilguven/bert_tr_turkish_hotel_reviews",
+    "electra": "anilguven/electra_tr_turkish_hotel_reviews",
+}
+
+MODEL_HOTELS = ["albert","distilbert","bert","electra"]
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+# Create a mapping from formatted model names to their original identifiers
+def format_model_name(model_key):
+    name_parts = model_key
+    formatted_name = ''.join(name_parts)  # Join them into a single string with title case
+    return formatted_name
+
+formatted_names_to_identifiers = {
+    format_model_name(key): key for key in MODEL_HOTEL.keys()
+}
+
+# Debug to ensure names are formatted correctly
+#st.write("Formatted Model Names to Identifiers:", formatted_names_to_identifiers
+
+with st.expander("About this app"):
+    st.write(f"""
+    1-Choose your model for hotel review analysis (negative or positive).\n
+    2-Enter your sample text.\n
+    3-And model predict your text's result.
+    """)
+
+model_name: str = st.selectbox("Model", options=MODEL_HOTELS)
+selected_model = MODEL_HOTEL[model_name]
+
+if not hf_key:
+    st.info("Please add your HuggingFace Access Key to continue.")
+    st.stop()
+
+access_token = hf_key
+pipe = pipeline("text-classification", model=selected_model, token=access_token)
+
+#from transformers import AutoTokenizer, AutoModelForSequenceClassification
+#tokenizer = AutoTokenizer.from_pretrained(selected_model)
+#pipe = AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path=selected_model)
+
+# Display the selected model using the formatted name
+model_display_name = selected_model  # Already formatted
+st.write(f"Model being used: `{model_display_name}`")
+
+
+comment = st.text_input("Enter your text for analysis")#User input
+
+st.text('')
+if st.button("Submit for Analysis"):#User Review Button
+    if not hf_key:
+        st.info("Please add your HuggingFace Access Key to continue.")
+        st.stop()
+    else:
+        result = pipe(comment)[0]
+        label=''
+        if result["label"] == "LABEL_0": label = "Negative"
+        else: label = "Positive"
+        st.text(label + " comment with " + str(result["score"]) + " accuracy")
+
+

pages/2_File_Upload.py

@@ -0,0 +1,148 @@
+import streamlit as st
+import pandas as pd
+
+st.set_page_config(page_title="Turkish Review Analysis - via AG", page_icon='📖')
+st.header("📖Review Analysis for Your File - TR")
+
+with st.sidebar:
+    hf_key = st.text_input("HuggingFace Access Key", key="hf_key", type="password")
+
+MODEL_HOTEL = {
+    "albert": "anilguven/albert_tr_turkish_hotel_reviews",  # Add the emoji for the Meta-Llama model
+    "distilbert": "anilguven/distilbert_tr_turkish_hotel_reviews",
+    "bert": "anilguven/bert_tr_turkish_hotel_reviews",
+    "electra": "anilguven/electra_tr_turkish_hotel_reviews",
+}
+
+MODEL_MOVIE = {
+    "albert": "anilguven/albert_tr_turkish_movie_reviews",  # Add the emoji for the Meta-Llama model
+    "distilbert": "anilguven/distilbert_tr_turkish_movie_reviews",
+    "bert": "anilguven/bert_tr_turkish_movie_reviews",
+    "electra": "anilguven/electra_tr_turkish_movie_reviews",
+}
+
+MODELS = ["albert","distilbert","bert","electra"]
+MODEL_TASK = ["Movie review analysis","Hotel review analysis"]
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+# Create a mapping from formatted model names to their original identifiers
+def format_model_name(model_key):
+    name_parts = model_key
+    formatted_name = ''.join(name_parts)  # Join them into a single string with title case
+    return formatted_name
+
+formatted_names_to_identifiers = {
+    format_model_name(key): key for key in MODEL_HOTEL.keys()
+}
+
+# Debug to ensure names are formatted correctly
+#st.write("Formatted Model Names to Identifiers:", formatted_names_to_identifiers
+
+with st.expander("About this app"):
+    st.write(f"""
+    1-Upload your file as txt or csv file. Each file contains one sample in the each row.\n
+    2-Choose your task (movie or hotel review)
+    3-Choose your model according to your task analysis (negative or positive).\n
+    4-And model predict your text files. \n
+    5-Download your test results.
+    """)
+
+st.text('')
+
+uploaded_file = st.file_uploader(
+    "Upload a csv or txt file",
+    type=["csv", "txt"],
+    help="Scanned documents are not supported yet!",
+)
+
+if not uploaded_file or not hf_key:
+    st.stop()
+
+
+@st.cache_data
+def convert_df(df):
+    # IMPORTANT: Cache the conversion to prevent computation on every rerun
+    return df.to_csv().encode("utf-8")
+
+datas = [] 
+try:
+    if uploaded_file.name.lower().endswith(".csv"):
+        text = uploaded_file.read().decode("utf-8", errors="replace")
+        datas = text.split("\n")
+        with st.expander("Show Datas"):
+            st.text(datas)
+    elif uploaded_file.name.lower().endswith(".txt"):
+        text = uploaded_file.read().decode("utf-8", errors="replace")
+        datas = text.split("\n")
+        with st.expander("Show Datas"):
+            st.text(datas)
+    else:
+        raise NotImplementedError(f"File type {uploaded_file.name.split('.')[-1]} not supported")
+except Exception as e:
+    st.error("Error reading file. Make sure the file is not corrupted or encrypted")
+    st.stop()
+
+task_name: str = st.selectbox("Task", options=MODEL_TASK)
+model_select = ''
+if task_name == "Movie review analysis": model_select = MODEL_MOVIE
+else: model_select = MODEL_HOTEL
+
+model_name: str = st.selectbox("Model", options=MODELS)
+selected_model = model_select[model_name]
+
+if not hf_key:
+    st.info("Please add your HuggingFace Access Key to continue.")
+    st.stop()
+
+access_token = hf_key
+pipe = pipeline("text-classification", model=selected_model, token=access_token)
+
+#from transformers import AutoTokenizer, AutoModelForSequenceClassification
+#tokenizer = AutoTokenizer.from_pretrained(selected_model)
+#pipe = AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path=selected_model)
+
+# Display the selected model using the formatted name
+model_display_name = selected_model  # Already formatted
+st.write(f"Model being used: `{model_display_name}`")
+
+results=[]
+txt = ''
+labels=[]
+accuracies=[]
+values=[]
+if st.button("Submit for File Analysis"):#User Review Button
+    if not hf_key:
+        st.info("Please add your HuggingFace Access Key to continue.")
+        st.stop()
+    else:    
+        label=''
+        for data in datas:
+            result = pipe(data)[0]
+            if result["label"] == "LABEL_0": label = "Negative"
+            else: label = "Positive"
+            results.append(data[:-1] + ", " + label + ", " + str(result["score"]*100) + "\n")
+            labels.append(label)
+            accuracies.append(str(result["score"]*100))
+            values.append(data[:-1])
+            txt += data[:-1] + ", " + label + ", " + str(result["score"]*100) + "\n"
+        
+        st.text("All files evaluated. You'll download result file.")
+        if uploaded_file.name.lower().endswith(".txt"):
+            with st.expander("Show Results"):
+                st.write(results)
+            st.download_button('Download Result File', txt, uploaded_file.name.lower()[:-4] + "_results.txt")
+
+        elif uploaded_file.name.lower().endswith(".csv"):
+            dataframe = pd.DataFrame({ "text": values,"label": labels,"accuracy": accuracies})
+            with st.expander("Show Results"):
+                st.write(dataframe)
+            csv = convert_df(dataframe)
+            st.download_button(label="Download as CSV",data=csv,file_name=uploaded_file.name.lower()[:-4] + "_results.csv",mime="text/csv")
+        else:
+            raise NotImplementedError(f"File type not supported")
+
+ #   with open(result_file) as f:
+ #       st.download_button('Download Txt file', f)
+
+

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+transformers
+torch
+sentencepiece