data that produces dict(flask.request.args) = {"name": "A", "id": "1"} IP:5000/data?name=A&id=1 IP:5000/data?name="A"&id=1 IP:5000/data?name=A,id=1 IP:5000/data?name="A",id=1 home.html of the site? @app.route("/img.png")
def png():
print("X")
return ""
@app.route("/img.svg")
def svg():
print("Y")
return ""
@app.route("/home.html")
def home():
print("Z")
return "<html><body><img src="img.svg"></body></html>"
Ignore the order the letters are printed: | - | click | no-click |
| Version A | 1 | 2 |
| Version B | 3 | 4 |
scipy.stats.fisher_exact(df) returns 0.001 for table 1, 0.01 for table 2, and 0.1 for table 3. At a threshold for significance of 5 percent, for how many tests do we have statistically significant evidence that B has a different click-through-rate than A?
@app.route("/aaa.html")
def aaa():
return "bbb"
@app.route("/")
def bbb():
return "aaa"
http://127.0.0.1:5000/ http://127.0.0.1:5000/aaa http://127.0.0.1:5000/aaa.html http://127.0.0.1:5000/bbb | Version | LCB | CTR | UCB |
| A | 0.4 | 0.5 | 0.6 |
| B | 0 | 0.4 | 0.8 |
| C | 0.1 | 0.3 | 0.5 |
| D | -0.3 | 0.2 | 0.7 |
Last Updated: November 03, 2025 at 1:01 PM