Upload 3 files
Browse files- Dockefile +11 -0
- app.py +68 -0
- requirements.txt +2 -0
Dockefile
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM python:3.9
|
| 2 |
+
|
| 3 |
+
WORKDIR /code
|
| 4 |
+
|
| 5 |
+
COPY ./requirements.txt /code/requirements.txt
|
| 6 |
+
|
| 7 |
+
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
|
| 8 |
+
|
| 9 |
+
COPY . .
|
| 10 |
+
|
| 11 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
app.py
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI, UploadFile, File
|
| 2 |
+
from fastapi.responses import HTMLResponse
|
| 3 |
+
import pandas as pd
|
| 4 |
+
import io
|
| 5 |
+
import requests
|
| 6 |
+
import time
|
| 7 |
+
|
| 8 |
+
app = FastAPI()
|
| 9 |
+
|
| 10 |
+
@app.get("/", response_class=HTMLResponse)
|
| 11 |
+
async def analyze_logs():
|
| 12 |
+
return """
|
| 13 |
+
<html>
|
| 14 |
+
<body>
|
| 15 |
+
<form action="/upload/" enctype="multipart/form-data" method="post">
|
| 16 |
+
<input name="file" type="file">
|
| 17 |
+
<input type="submit">
|
| 18 |
+
</form>
|
| 19 |
+
</body>
|
| 20 |
+
</html>
|
| 21 |
+
"""
|
| 22 |
+
|
| 23 |
+
@app.post("/upload/")
|
| 24 |
+
async def upload_file(file: UploadFile = File(...)):
|
| 25 |
+
contents = await file.read()
|
| 26 |
+
logs_df = pd.read_parquet(io.BytesIO(contents))
|
| 27 |
+
|
| 28 |
+
processing_message = "\n\n Processing files...\n\n"
|
| 29 |
+
time.sleep(3) # Simulate processing time (3 seconds)
|
| 30 |
+
|
| 31 |
+
logs_df['datetime'] = pd.to_datetime(logs_df['datetime'], format='%d/%m/%Y:%H:%M:%S')
|
| 32 |
+
logs_df['day'] = logs_df['datetime'].apply(lambda x: x.day)
|
| 33 |
+
logs_df['hour'] = logs_df['datetime'].apply(lambda x: x.hour)
|
| 34 |
+
logs_df['minute'] = logs_df['datetime'].apply(lambda x: x.minute)
|
| 35 |
+
|
| 36 |
+
ip_address_count_df = (
|
| 37 |
+
logs_df.groupby(['method', 'client'], as_index=False)
|
| 38 |
+
.size()
|
| 39 |
+
.rename(columns={'size': 'count'})
|
| 40 |
+
.sort_values('count', ascending=False)
|
| 41 |
+
)
|
| 42 |
+
|
| 43 |
+
ip_address_count_df = ip_address_count_df.assign(
|
| 44 |
+
perc=ip_address_count_df['count'].div(ip_address_count_df['count'].sum()),
|
| 45 |
+
cum_perc=lambda df: df['perc'].cumsum(),
|
| 46 |
+
)
|
| 47 |
+
|
| 48 |
+
result = (
|
| 49 |
+
"<h1>Redundant IP Requests....</h1>"
|
| 50 |
+
"<p>The Total API Requests from the sample logs are : {total_requests}</p>"
|
| 51 |
+
"<p>The Redundant API Requests from the sample logs are : {redundant_requests}</p>"
|
| 52 |
+
"<p>The percentage of Redundant API Requests from the sample logs is : {redundant_percentage:.2f}%</p>"
|
| 53 |
+
"{dataframe_html}"
|
| 54 |
+
).format(
|
| 55 |
+
total_requests=logs_df.shape[0],
|
| 56 |
+
redundant_requests=ip_address_count_df.shape[0],
|
| 57 |
+
redundant_percentage=(ip_address_count_df.shape[0] / logs_df.shape[0]) * 100,
|
| 58 |
+
dataframe_html=ip_address_count_df.head(1000)
|
| 59 |
+
.style.background_gradient(subset=['count', 'perc', 'cum_perc'], cmap='cividis')
|
| 60 |
+
.format({'count': '{:,}', 'perc': '{:.1%}', 'cum_perc': '{:.1%}'})
|
| 61 |
+
.render(),
|
| 62 |
+
)
|
| 63 |
+
|
| 64 |
+
# Save result in a new HTML file
|
| 65 |
+
with open("result.html", "w") as f:
|
| 66 |
+
f.write(result)
|
| 67 |
+
|
| 68 |
+
return "Result saved in 'result.html'"
|
requirements.txt
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
fastapi
|
| 2 |
+
pandas
|