Spaces:
Sleeping
Sleeping
File size: 3,364 Bytes
dd65c5d |
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 |
import streamlit as st
import pandas as pd
import os
from utils import save_json, load_json
from markdown import markdown
from utils import load_json
from autoviz import AutoViz_Class
import base64
from google.cloud import aiplatform
import base64
import vertexai
from vertexai.preview.generative_models import GenerativeModel, Part
import json
#setup cloud
aiplatform.init(
project = "geminsights",
location="us-central1"
)
json_file = json.loads(st.secrets["credentials"], strict=False)
with open("credentials.json", "w") as f:
json.dump(json_file, f, indent=2)
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "credentials.json"
dataframe = None
st.title("GemInsights 📊")
st.caption('A gemini powered data analysis tool to get insights from data 🔥')
file = st.file_uploader(
"Pick a dataframe", type=["csv", "xlsx"], accept_multiple_files=False
)
if file is not None:
_, extension = os.path.splitext(file.name)
if extension == ".csv":
dataframe = pd.read_csv(file)
else:
dataframe = pd.read_excel(file)
st.write(dataframe.head())
st.write(f"updated a dataframe with shape {dataframe.shape}")
if file is not None:
text_input = st.text_input(
"Enter something about the data 👇",
label_visibility="visible",
disabled=False,
placeholder="eg:- This is a sales dataframe",
)
option = st.selectbox(
"Which is the target column ? 🎯",
tuple(list(dataframe.columns)),
index=None,
placeholder="Select one column in here",
)
def plot(dataframe, target):
AV = AutoViz_Class()
dft = AV.AutoViz(
"",
sep=",",
depVar=target,
dfte=dataframe,
header=0,
verbose=2,
lowess=False,
chart_format="jpg",
max_rows_analyzed=500,
max_cols_analyzed=20,
save_plot_dir="plots",
)
def prompt_make(dataframe, target, info):
images = []
image_dir = f"plots/{target}"
image_files = os.listdir(image_dir)
for image_file in image_files:
image_path = os.path.join(image_dir, image_file)
img = open(image_path, "rb").read()
img_bytes = Part.from_data(
base64.b64decode(base64.encodebytes(img)), mime_type="image/jpeg"
)
images.append(img_bytes)
with open("prompt.txt", "rb") as file:
data = file.read()
prompt = f"{data}\n Here are some of the informations related to the dataset - '{info}'"
# print(f"{prompt}")
# print(images)
return prompt, images
def generate_res(prompt, images):
print("prompting ...")
model = GenerativeModel("gemini-pro-vision")
responses = model.generate_content(
[prompt]+images,
generation_config={
"max_output_tokens": 2048,
"temperature": 0.4,
"top_p": 1,
"top_k": 32
},
)
return responses.text
def generate(dataframe, text_input, option):
plot(dataframe, option)
prompt, images = prompt_make(dataframe, option, text_input)
res = generate_res(prompt, images)
return res
if st.button("Get Insights", type="primary"):
st.write("generating insights ⏳ ... ")
# running the pipeline
response = generate(dataframe, text_input, option)
res = markdown(response)
st.markdown(res, unsafe_allow_html=True)
else:
st.write("")
|