File size: 4,617 Bytes
fa3d6a7 b6a7af0 fa3d6a7 38614a2 fa3d6a7 02f3534 fa3d6a7 38614a2 fa3d6a7 38614a2 fa3d6a7 87c4f81 fa3d6a7 38614a2 fa3d6a7 |
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 |
import chainlit as cl
import pandas as pd
import io
import matplotlib.pyplot as plt
import base64
from io import BytesIO
from pandasai import SmartDataframe
import pandas as pd
from pandasai.llm import OpenAI
from io import StringIO
import matplotlib.pyplot as plt
import csv
from collections import defaultdict
import os
got_csv = False
def find_most_valuable_feature(csv_file):
print("find_most_valuable_feature")
print(csv_file)
smart_llm = OpenAI(api_token=os.environ["OPENAI_API_KEY"])
# Initialize a defaultdict to store column data
columns = defaultdict(list)
# Read the CSV file and populate the defaultdict
with open("upload.csv") as f:
reader = csv.reader(f)
headers = next(reader)
for row in reader:
for header, value in zip(headers, row):
columns[header].append(value)
# Manually create a DataFrame from the defaultdict
smart_df = pd.DataFrame({
"ID": columns["ID"],
"Date and Time": columns["Date and Time"],
"Business Unit": columns["Business Unit"],
"Usage Change": columns["Usage Change"],
"Wolftech Improvement": columns["Wolftech Improvement"],
"Likelihood to Recommend": columns["Likelihood to Recommend"],
"Effective Training": columns["Effective Training"],
"Most Valuable Feature": columns["Most Valuable Feature"]
})
smart_df = SmartDataframe(smart_df, config={"llm": smart_llm})
out = smart_df.chat('Summarize the top three "Most Valuable Feature" for people where Usage Changed was Increased?')
print(out)
df = out
# Plotting
plt.figure(figsize=(10, 6))
plt.bar(df["Most Valuable Feature"], df["Count"], color='blue')
plt.xlabel('Most Valuable Feature')
plt.ylabel('Count')
plt.title('Count of Most Valuable Features')
plt.xticks(rotation=45, ha="right") # Rotate labels for better readability
plt.tight_layout() # Adjust layout for better fit
# Save the plot to a BytesIO object
image_buffer = BytesIO()
plt.savefig(image_buffer, format='png')
image_buffer.seek(0)
return image_buffer
def process_and_analyze_data(csv_file):
# Read CSV file
csv_data = pd.read_csv(csv_file)
# Logging to check data loading
print(f"CSV Data Loaded: {csv_data.head()}")
# Count of responses in each category of 'Business Unit'
business_unit_counts = csv_data['Business Unit'].value_counts()
# Plotting the count of responses in each 'Business Unit' category
plt.figure(figsize=(10, 6))
business_unit_counts.plot(kind='bar')
plt.title('Count of Responses by Business Unit')
plt.xlabel('Business Unit')
plt.ylabel('Count')
plt.xticks(rotation=45)
plt.tight_layout()
# Save the plot to a BytesIO object
image_buffer = BytesIO()
plt.savefig(image_buffer, format='png')
image_buffer.seek(0)
return image_buffer
# Function to handle message events
@cl.on_message
async def handle_message(message: cl.Message):
global got_csv
# Retrieve the CSV file from the message
csv_file = next(
(
io.BytesIO(file.content)
for file in message.elements or []
if file.mime and "csv" in file.mime
),
None,
)
# Logging to check file retrieval
print(f"CSV File: {csv_file}")
if csv_file:
got_csv = True
try:
image_buffer = find_most_valuable_feature(csv_file)
# Get bytes data from BytesIO object and send the image data
image_data = image_buffer.getvalue()
name = "chart"
cl.user_session.set(name, image_data)
cl.user_session.set("generated_image", name)
await cl.Message(content="Based on the people who increased usage, here are the most valuable features...").send()
generated_image = cl.user_session.get(name)
elements = []
actions = []
elements = [
cl.Image(
content=generated_image,
name=name,
display="inline",
size="large"
)
]
await cl.Message(content=name, elements=elements, actions=actions).send()
except Exception as e:
await cl.Message(content=f"An error occurred: {str(e)}").send()
else:
if not got_csv:
await cl.Message(content="Please upload a CSV file.").send()
# Run the ChainLit app
if __name__ == "__main__":
cl.run()
|