Duplicate from king007/table_questions

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Table Questions
+emoji: 🐠
+colorFrom: red
+colorTo: red
+sdk: gradio
+sdk_version: 3.16.2
+app_file: app.py
+pinned: false
+duplicated_from: king007/table_questions
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,72 @@
+import gradio as gr
+import pandas as pd
+from transformers import (
+    AutoModelForSeq2SeqLM,
+    AutoModelForTableQuestionAnswering,
+    AutoTokenizer,
+    pipeline,
+)
+
+model_tapex = "microsoft/tapex-large-finetuned-wtq"
+tokenizer_tapex = AutoTokenizer.from_pretrained(model_tapex)
+model_tapex = AutoModelForSeq2SeqLM.from_pretrained(model_tapex)
+pipe_tapex = pipeline(
+    "table-question-answering", model=model_tapex, tokenizer=tokenizer_tapex
+)
+
+model_tapas = "google/tapas-large-finetuned-wtq"
+tokenizer_tapas = AutoTokenizer.from_pretrained(model_tapas)
+model_tapas = AutoModelForTableQuestionAnswering.from_pretrained(model_tapas)
+pipe_tapas = pipeline(
+    "table-question-answering", model=model_tapas, tokenizer=tokenizer_tapas
+)
+
+
+def process(query, file, correct_answer, rows=20):
+    table = pd.read_csv(file.name, header=0).astype(str)
+    table = table[:rows]
+    result_tapex = pipe_tapex(table=table, query=query)
+    result_tapas = pipe_tapas(table=table, query=query)
+    return result_tapex["answer"], result_tapas["answer"], correct_answer
+
+
+# Inputs
+query_text = gr.Text(label="Enter a question")
+input_file = gr.File(label="Upload a CSV file", type="file")
+rows_slider = gr.Slider(label="Number of rows")
+
+# Output
+answer_text_tapex = gr.Text(label="TAPEX answer")
+answer_text_tapas = gr.Text(label="TAPAS answer")
+
+description = "This Space lets you ask questions on CSV documents with Microsoft [TAPEX-Large](https://huggingface.co/microsoft/tapex-large-finetuned-wtq) and Google [TAPAS-Large](https://huggingface.co/google/tapas-large-finetuned-wtq). \
+Both have been fine-tuned on the [WikiTableQuestions](https://huggingface.co/datasets/wikitablequestions) dataset. \n\n\
+A sample file with football statistics is available in the repository: \n\n\
+* Which team has the most wins? Answer: Manchester City FC\n\
+* Which team has the most wins: Chelsea, Liverpool or Everton? Answer: Liverpool\n\
+* Which teams have scored less than 40 goals? Answer: Cardiff City FC, Fulham FC, Brighton & Hove Albion FC, Huddersfield Town FC\n\
+* What is the average number of wins? Answer: 16 (rounded)\n\n\
+You can also upload your own CSV file. Please note that maximum sequence length for both models is 1024 tokens, \
+so you may need to limit the number of rows in your CSV file. Chunking is not implemented yet."
+
+iface = gr.Interface(
+    theme="huggingface",
+    description=description,
+    layout="vertical",
+    fn=process,
+    inputs=[query_text, input_file, rows_slider],
+    outputs=[answer_text_tapex, answer_text_tapas],
+    examples=[
+        ["Which team has the most wins?", "default_file.csv", 20],
+        [
+            "Which team has the most wins: Chelsea, Liverpool or Everton?",
+            "default_file.csv",
+            20,
+        ],
+        ["Which teams have scored less than 40 goals?", "default_file.csv", 20],
+        ["What is the average number of wins?", "default_file.csv", 20],
+    ],
+    allow_flagging="never",
+)
+
+iface.launch()

app2.py

@@ -0,0 +1,72 @@
+import gradio as gr
+import pandas as pd
+from transformers import (
+    AutoModelForSeq2SeqLM,
+    AutoModelForTableQuestionAnswering,
+    AutoTokenizer,
+    pipeline,
+)
+
+model_tapex = "microsoft/tapex-large-finetuned-wtq"
+tokenizer_tapex = AutoTokenizer.from_pretrained(model_tapex)
+model_tapex = AutoModelForSeq2SeqLM.from_pretrained(model_tapex)
+pipe_tapex = pipeline(
+    "table-question-answering", model=model_tapex, tokenizer=tokenizer_tapex
+)
+
+model_tapas = "google/tapas-large-finetuned-wtq"
+tokenizer_tapas = AutoTokenizer.from_pretrained(model_tapas)
+model_tapas = AutoModelForTableQuestionAnswering.from_pretrained(model_tapas)
+pipe_tapas = pipeline(
+    "table-question-answering", model=model_tapas, tokenizer=tokenizer_tapas
+)
+
+
+def process(query, file, correct_answer, rows=20):
+    table = pd.read_csv(file.name, header=0).astype(str)
+    table = table[:rows]
+    result_tapex = pipe_tapex(table=table, query=query)
+    result_tapas = pipe_tapas(table=table, query=query)
+    return result_tapex["answer"], result_tapas["answer"], correct_answer
+
+
+# Inputs
+query_text = gr.Text(label="Enter a question")
+input_file = gr.File(label="Upload a CSV file", type="file")
+rows_slider = gr.Slider(label="Number of rows")
+
+# Output
+answer_text_tapex = gr.Text(label="TAPEX answer")
+answer_text_tapas = gr.Text(label="TAPAS answer")
+
+description = "This Space lets you ask questions on CSV documents with Microsoft [TAPEX-Large](https://huggingface.co/microsoft/tapex-large-finetuned-wtq) and Google [TAPAS-Large](https://huggingface.co/google/tapas-large-finetuned-wtq). \
+Both have been fine-tuned on the [WikiTableQuestions](https://huggingface.co/datasets/wikitablequestions) dataset. \n\n\
+A sample file with football statistics is available in the repository: \n\n\
+* Which team has the most wins? Answer: Manchester City FC\n\
+* Which team has the most wins: Chelsea, Liverpool or Everton? Answer: Liverpool\n\
+* Which teams have scored less than 40 goals? Answer: Cardiff City FC, Fulham FC, Brighton & Hove Albion FC, Huddersfield Town FC\n\
+* What is the average number of wins? Answer: 16 (rounded)\n\n\
+You can also upload your own CSV file. Please note that maximum sequence length for both models is 1024 tokens, \
+so you may need to limit the number of rows in your CSV file. Chunking is not implemented yet."
+
+iface = gr.Interface(
+    theme="huggingface",
+    description=description,
+    layout="vertical",
+    fn=process,
+    inputs=[query_text, input_file, rows_slider],
+    outputs=[answer_text_tapex, answer_text_tapas],
+    examples=[
+        ["Which team has the most wins?", "default_file.csv", 20],
+        [
+            "Which team has the most wins: Chelsea, Liverpool or Everton?",
+            "default_file.csv",
+            20,
+        ],
+        ["Which teams have scored less than 40 goals?", "default_file.csv", 20],
+        ["What is the average number of wins?", "default_file.csv", 20],
+    ],
+    allow_flagging="never",
+)
+
+iface.launch()

app3.py

@@ -0,0 +1,16 @@
+from transformers import pipeline
+import pandas as pd
+
+# prepare table + question
+data = {"Actors": ["Brad Pitt", "Leonardo Di Caprio", "George Clooney"], "Number of movies": ["87", "53", "69"]}
+table = pd.DataFrame.from_dict(data)
+question = "how many movies does Leonardo Di Caprio have?"
+
+# pipeline model
+# Note: you must to install torch-scatter first.
+tqa = pipeline(task="table-question-answering", model="google/tapas-large-finetuned-wtq")
+
+# result
+
+print(tqa(table=table, query=query)['cells'][0])
+#53

default_file.csv

@@ -0,0 +1,21 @@
+team_name,common_name,wins,draws,draws_home,draws_away,losses,points_per_game,league_position,goals_scored,goals_conceded,goal_difference,total_goal_count
+Arsenal FC,Arsenal,21,7,3,4,10,1.84,5,73,51,22,124
+Tottenham Hotspur FC,Tottenham Hotspur,23,2,2,0,13,1.87,4,67,39,28,106
+Manchester City FC,Manchester City,32,2,0,2,4,2.58,1,95,23,72,118
+Leicester City FC,Leicester City,15,7,3,4,16,1.37,9,51,48,3,99
+Crystal Palace FC,Crystal Palace,14,7,5,2,17,1.29,12,51,53,-2,104
+Everton FC,Everton,15,9,4,5,14,1.42,8,54,46,8,100
+Burnley FC,Burnley,11,7,2,5,20,1.05,15,45,68,-23,113
+Southampton FC,Southampton,9,12,8,4,17,1.03,16,45,65,-20,110
+AFC Bournemouth,AFC Bournemouth,13,6,5,1,19,1.18,14,56,70,-14,126
+Manchester United FC,Manchester United,19,9,6,3,10,1.74,6,65,54,11,119
+Liverpool FC,Liverpool,30,7,2,5,1,2.55,2,89,22,67,111
+Chelsea FC,Chelsea,21,9,6,3,8,1.89,3,63,39,24,102
+West Ham United FC,West Ham United,15,7,4,3,16,1.37,10,52,55,-3,107
+Watford FC,Watford,14,8,3,5,16,1.32,11,52,59,-7,111
+Newcastle United FC,Newcastle United,12,9,1,8,17,1.18,13,42,48,-6,90
+Cardiff City FC,Cardiff City,10,4,2,2,24,0.89,18,34,69,-35,103
+Fulham FC,Fulham,7,5,3,2,26,0.68,19,34,81,-47,115
+Brighton & Hove Albion FC,Brighton & Hove Albion,9,9,5,4,20,0.95,17,35,60,-25,95
+Huddersfield Town FC,Huddersfield Town,3,7,3,4,28,0.42,20,22,76,-54,98
+Wolverhampton Wanderers FC,Wolverhampton Wanderers,16,9,4,5,13,1.5,7,47,46,1,93

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+torch