Spaces:
Sleeping
Sleeping
File size: 8,931 Bytes
3673798 a894fcd 3673798 a894fcd 3673798 4b9f242 3673798 4b9f242 a894fcd 3673798 4b9f242 3673798 4b9f242 3673798 4b9f242 3673798 4b9f242 3673798 a894fcd 3673798 a894fcd da84618 a894fcd 3673798 a894fcd 3673798 cb5868e 3673798 4b9f242 3673798 a894fcd 3673798 cb5868e a894fcd a557d1a a894fcd 3673798 cfbd3ec 3673798 cb5868e a894fcd 3673798 a894fcd 3673798 4b9f242 3673798 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
import streamlit as st
import time
import pandas as pd
import io
from transformers import pipeline
from streamlit_extras.stylable_container import stylable_container
import json
import plotly.express as px
st.subheader("AI CSV and XLSX Data Analyzer", divider="blue")
st.link_button("by nlpblogs", "https://nlpblogs.com", type = "tertiary")
expander = st.expander("**Important notes on the AI CSV and XLSX Data Analyzer**")
expander.write('''
**Supported File Formats:**
This app accepts files in .csv and .xlsx formats.
**How to Use:**
Upload your file first. Select two different columns from your data to visualize in a tree map. Then, type your question into the text area provided and click the 'Retrieve your answer' button.
**Usage Limits:**
You can ask up to 5 questions.
**Subscription Management:**
This app offers a one-day free trial, followed by a one-day subscription, expiring after 24 hours. If you are interested in building your own AI CSV and XLSX Data Analyzer, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app in five business days. If you wish to delete your Account with us, please contact us at [email protected]
**Customization:**
To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
**File Handling and Errors:**
The app may display an error message if your file has errors or date values.
For any errors or inquiries, please contact us at [email protected]
''')
with st.sidebar:
container = st.container(border=True)
container.write("**Question-Answering (QA)** is the task of retrieving the answer to a question from a given text (knowledge base), which is used as context.")
st.subheader("Related NLP Web Apps", divider = "blue")
st.link_button("AI Google Sheet Data Analyzer", "https://nlpblogs.com/shop/table-question-answering-qa/google-sheet-qa-demo-app/", type = "primary")
if 'question_attempts' not in st.session_state:
st.session_state['question_attempts'] = 0
max_attempts = 5
upload_file = st.file_uploader("Upload your file. Accepted file formats include: .csv, .xlsx", type=['csv', 'xlsx'])
if upload_file is not None:
file_extension = upload_file.name.split('.')[-1].lower()
if file_extension == 'csv':
try:
df = pd.read_csv(upload_file, na_filter=False)
if df.isnull().values.any():
st.error("Error: The CSV file contains missing values.")
st.stop()
else:
new_columns = [f'column_{i+1}' for i in range(len(df.columns))]
df.columns = new_columns
all_columns = df.columns.tolist()
st.subheader("Select columns for the Tree Map", divider="blue")
parent_column = st.selectbox("Select the parent column:", all_columns)
value_column = st.selectbox("Select the value column:", all_columns)
if parent_column and value_column:
if parent_column == value_column:
st.warning("Warning: You have selected the same column for both the parent and value column. Please select two different columns from your data.")
elif parent_column and value_column:
path_columns = [px.Constant("all"), parent_column, value_column]
fig = px.treemap(df,
path=path_columns)
fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
st.subheader("Tree map", divider="red")
st.plotly_chart(fig)
st.session_state.df = df
except pd.errors.ParserError:
st.error("Error: The CSV file is not readable or is incorrectly formatted.")
st.stop()
except UnicodeDecodeError:
st.error("Error: The CSV file could not be decoded.")
st.stop()
except Exception as e:
st.error(f"An unexpected error occurred while reading CSV: {e}")
st.stop()
elif file_extension == 'xlsx':
try:
df = pd.read_excel(upload_file, na_filter=False)
if df.isnull().values.any():
st.error("Error: The Excel file contains missing values.")
st.stop()
else:
new_columns = [f'column_{i+1}' for i in range(len(df.columns))]
df.columns = new_columns
all_columns = df.columns.tolist()
st.subheader("Select columns for the Tree Map", divider="blue")
parent_column = st.selectbox("Select the parent column:", all_columns)
value_column = st.selectbox("Select the value column:", all_columns)
if parent_column and value_column:
if parent_column == value_column:
st.warning("Warning: You have selected the same column for both the parent and value column. Please select two different columns from your data.")
elif parent_column and value_column:
path_columns = [px.Constant("all"), parent_column, value_column]
fig = px.treemap(df,
path=path_columns)
fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
st.subheader("Tree map", divider="red")
st.plotly_chart(fig)
st.session_state.df = df
except ValueError:
st.error("Error: The Excel file is not readable or is incorrectly formatted.")
st.stop()
except Exception as e:
st.error(f"An unexpected error occurred while reading Excel: {e}")
st.stop()
else:
st.warning("Unsupported file type.")
st.stop()
st.divider()
if upload_file is not None:
file_extension = upload_file.name.split('.')[-1].lower()
if file_extension == 'csv':
try:
df = pd.read_csv(upload_file, na_filter=False)
if df.isnull().values.any():
st.error("Error: The CSV file contains missing values.")
st.stop()
else:
st.dataframe(df, key="csv_dataframe")
st.write("_number of rows_", df.shape[0])
st.write("_number of columns_", df.shape[1])
st.session_state.df = df
except pd.errors.ParserError:
st.error("Error: The CSV file is not readable or is incorrectly formatted.")
st.stop()
except UnicodeDecodeError:
st.error("Error: The CSV file could not be decoded.")
st.stop()
except Exception as e:
st.error(f"An unexpected error occurred while reading CSV: {e}")
st.stop()
elif file_extension == 'xlsx':
try:
df = pd.read_excel(upload_file, na_filter=False)
if df.isnull().values.any():
st.error("Error: The Excel file contains missing values.")
st.stop()
else:
st.dataframe(df, key="excel_dataframe")
st.write("_number of rows_", df.shape[0])
st.write("_number of columns_", df.shape[1])
st.session_state.df = df
except ValueError:
st.error("Error: The Excel file is not readable or is incorrectly formatted.")
st.stop()
except Exception as e:
st.error(f"An unexpected error occurred while reading Excel: {e}")
st.stop()
else:
st.warning("Unsupported file type.")
st.stop()
def clear_question():
st.session_state["question"] = ""
question = st.text_input("Type your question here and then press **Retrieve your answer**:", key="question")
st.button("Clear question", on_click=clear_question)
if st.button("Retrieve your answer"):
if st.session_state['question_attempts'] >= max_attempts:
st.error(f"You have asked {max_attempts} questions. Maximum question attempts reached.")
st.stop()
st.session_state['question_attempts'] += 1
with st.spinner("Wait for it...", show_time=True):
time.sleep(5)
if df is not None:
tqa = pipeline(task="table-question-answering", model="microsoft/tapex-large-finetuned-wtq")
st.write(tqa(table=df, query=question)['answer'])
st.divider()
st.write(f"Number of questions asked: {st.session_state['question_attempts']}/{max_attempts}") |