skypy/plot_profiles.py at main · rmseq/skypy · GitHub

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
# %%
from datetime import date

import pandas as pd
import plotly.express as px
from plotly.graph_objs import Figure

input_path = "data/profiles.csv"
output_dir = "plots"
cutoff_date = date(2024, 3, 1)


def plot_cdf(profiles: pd.DataFrame) -> Figure:
    cdf = profiles["last_activity"].value_counts().sort_index().cumsum().reset_index()
    cdf.columns = ["last_activity", "cumulative_count"]
    cdf["cumulative_count"] = cdf["cumulative_count"] / len(profiles)

    return px.line(
        cdf,
        x="last_activity",
        y="cumulative_count",
        title="",
        labels={"last_activity": "Date", "cumulative_count": ""},
    )


def plot_frequency(profiles: pd.DataFrame) -> Figure:
    activity_counts = profiles["last_activity"].value_counts().sort_index().reset_index()
    activity_counts.columns = ["last_activity", "frequency"]
    activity_counts["frequency"] = activity_counts["frequency"] / activity_counts["frequency"].sum()

    return px.bar(
        activity_counts,
        x="last_activity",
        y="frequency",
        title="Normalized Frequency of Followers' Last Activity",
        labels={"last_activity": "Date", "frequency": "Normalized Frequency"},
    )


# %%
df = pd.read_csv(input_path)

df["last_activity"] = pd.to_datetime(df["last_activity"], errors="coerce").dt.date
df["created_at"] = pd.to_datetime(df["created_at"], errors="coerce").dt.date

df = df[df["last_activity"] > cutoff_date]

# %% Followers
profiles = df[df["is_follower"]]

fig = plot_cdf(profiles)
fig.update_layout(
    title="CDF of Followers' Last Activity",
    xaxis_range=[
        (profiles["last_activity"].min() - pd.Timedelta(days=5)),  # Add margin to the left
        profiles["last_activity"].max() + pd.Timedelta(days=5),  # Add margin to the right
    ],
)

fig.write_html(f"{output_dir}/cdf_followers.html")
fig.write_image(f"{output_dir}/cdf_followers.png")

# %%
fig = plot_frequency(profiles)
fig.update_layout(
    title="Normalized Frequency of Followers' Last Activity",
)

fig.write_html(f"{output_dir}/frequency_followers.html")
fig.write_image(f"{output_dir}/frequency_followers.png")

print(f"Saved followers plots to {output_dir}/cdf_followers.[png|html] and {output_dir}/frequency_followers.[png|html]")

# %% Follows
profiles = df[df["is_follow"]]
fig = plot_cdf(profiles)
fig.update_layout(
    title="CDF of Follows' Last Activity",
    xaxis_range=[
        (profiles["last_activity"].min() - pd.Timedelta(days=5)),  # Add margin to the left
        profiles["last_activity"].max() + pd.Timedelta(days=5),  # Add margin to the right
    ],
)

fig.write_html(f"{output_dir}/cdf_follows.html")
fig.write_image(f"{output_dir}/cdf_follows.png")

# %%
fig = plot_frequency(profiles)
fig.update_layout(
    title="Normalized Frequency of Follows' Last Activity",
)
fig.write_html(f"{output_dir}/frequency_follows.html")
fig.write_image(f"{output_dir}/frequency_follows.png")

print(f"Saved follows plots to {output_dir}/cdf_follows.[png|html] and {output_dir}/frequency_follows.[png|html]")