Spaces:
Running
Running
File size: 3,841 Bytes
6a48f6a 6f38f2e 6a48f6a 6f38f2e eaead3f 6a48f6a eaead3f 6f38f2e 6a48f6a eaead3f 6a48f6a 6f38f2e 6a48f6a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
import gradio as gr
import pandas as pd
import numpy as np
from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
# summary function - test for single gradio function interfrace
def bulk_function(filename):
# Create class for data preparation
class SimpleDataset:
def __init__(self, tokenized_texts):
self.tokenized_texts = tokenized_texts
def __len__(self):
return len(self.tokenized_texts["input_ids"])
def __getitem__(self, idx):
return {k: v[idx] for k, v in self.tokenized_texts.items()}
# load tokenizer and model, create trainer
model_name = "j-hartmann/MindMiner-Binary"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
trainer = Trainer(model=model)
print(filename, type(filename))
print(filename.name)
# check type of input file
if filename.name.split(".")[1] == "csv":
print("entered")
# read file, drop index if exists
df_input = pd.read_csv(filename.name, index_col=False)
if df_input.columns[0] == "Unnamed: 0":
df_input = df_input.drop("Unnamed: 0", axis=1)
elif filename.name.split(".")[1] == "xlsx":
df_input = pd.read_excel(filename.name, index_col=False)
# handle Unnamed
if df_input.columns[0] == "Unnamed: 0":
df_input = df_input.drop("Unnamed: 0", axis=1)
else:
return
# read csv
# even if index given, drop it
#df_input = pd.read_csv(filename.name, index_col=False)
#print("df_input", df_input)
# expect csv format to be in:
# 1: ID
# 2: Texts
# no index
# store ids in ordered list
ids = df_input[df_input.columns[0]].to_list()
# store sentences in ordered list
# expects sentences to be in second col
# of csv with two cols
lines_s = df_input[df_input.columns[1]].to_list()
# Tokenize texts and create prediction data set
tokenized_texts = tokenizer(lines_s,truncation=True,padding=True)
pred_dataset = SimpleDataset(tokenized_texts)
# Run predictions -> predict whole df
predictions = trainer.predict(pred_dataset)
# Transform predictions to labels
preds = predictions.predictions.argmax(-1)
labels = pd.Series(preds).map(model.config.id2label)
scores = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1,keepdims=True)).max(1)
# round scores
scores_rounded = [round(score, 3) for score in scores]
# scores raw
temp = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1,keepdims=True))
# container
low = []
high = []
# extract scores (as many entries as exist in pred_texts)
for i in range(len(lines_s)):
low.append(round(temp[i][0], 3))
high.append(round(temp[i][1], 3))
# define df
df = pd.DataFrame(list(zip(ids,lines_s,labels,scores_rounded, low, high)), columns=[df_input.columns[0], df_input.columns[1],'max_label','max_score', 'low', 'high'])
print(df)
# save results to csv
YOUR_FILENAME = filename.name.split(".")[0] + "_MindMiner_Predictions" + ".csv" # name your output file
df.to_csv(YOUR_FILENAME, index=False)
# return dataframe for space output
return YOUR_FILENAME
gr.Interface(bulk_function, inputs=[gr.inputs.File(file_count="single", type="file", label="Upload file", optional=False),],
outputs=[gr.outputs.File(label="Output file")],
# examples=[["YOUR_FILENAME.csv"]], # computes, doesn't export df so far
theme="huggingface",
title="Apply MindMiner to Your CSV",
description="Upload csv file with 2 columns (in order): (a) ID column, (b) text column. The script returns a new file that includes both the ID column and text column together with the mind perception predictions using MindMiner.",
allow_flagging=False,
).launch(debug=True) |