Created
March 6, 2019 21:23
-
-
Save not7cd/99ed913b419c461a9d05e20205ae73dc to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding: utf-8 | |
""" | |
Messenger history analyzer and plotter | |
Short script to analyze past messages and create stackplot from them over time | |
USAGE | |
1. Download facebook data in json format | |
2. `cd` to facebook-your-name/messages | |
3. Run script here | |
""" | |
import numpy as np | |
import matplotlib.pyplot as plt | |
import glob | |
import json | |
import pandas as pd | |
from pandas.plotting import register_matplotlib_converters | |
register_matplotlib_converters() | |
def aggregate_msg_count(senders, participants): | |
tmp = [] | |
for p in participants: | |
single = senders[(senders["sender_name"] == p) & (senders["type"] == "Generic")] | |
single = single[["sender_name"]] | |
single["sender_name"].replace(p, 1, inplace=True) | |
single.rename(columns={"sender_name": p}, inplace=True) | |
count = single.groupby(pd.Grouper(freq="D")) | |
tmp.append(count.sum()) | |
out = pd.concat(tmp, axis=1) | |
return out | |
def aggregate_word_count(senders, participants): | |
tmp = [] | |
for p in participants: | |
single = senders[(senders["sender_name"] == p) & (senders["type"] == "Generic")] | |
single["content"] = single["content"].apply(lambda s: len(str(s).split(" "))) | |
single = single[["content"]] | |
single.rename(columns={"content": p}, inplace=True) | |
count = single.groupby(pd.Grouper(freq="D")) | |
tmp.append(count.sum()) | |
out = pd.concat(tmp, axis=1) | |
return out | |
def extract_msg_count(msgs, ignore=["Your Name"]): | |
df = pd.DataFrame(msgs["messages"]) | |
df_ = df[["timestamp_ms", "sender_name", "content", "type"]] | |
dti = pd.to_datetime(df_["timestamp_ms"].tolist(), unit="ms") | |
df_.index = dti | |
participants = [m["name"] for m in msgs["participants"] if m["name"] not in ignore] | |
if len(participants) > 3: | |
print(len(participants)) | |
raise ValueError("too big xd") | |
ppl = aggregate_word_count(df_, participants) | |
return ppl | |
def aggregate(df, top=12, freq="M"): | |
"""aggregate by chosen time span, return top""" | |
dfg = df.groupby(pd.Grouper(freq=freq)).sum() | |
top_cols = dfg.sum().sort_values(ascending=False)[:top] | |
top = dfg.loc[:, dfg.columns.isin(top_cols.index.tolist())] | |
return top.reindex(top_cols.index[::-1], axis=1) | |
def stackplot_messages(df, legend=False): | |
df = df.resample("D").interpolate(method="pchip") | |
plt.style.use("default") | |
fig, ax = plt.subplots(figsize=(20, 6)) | |
n_lines = 12 | |
x = np.linspace(0, 10) | |
phase_shift = np.linspace(0, np.pi, n_lines) | |
ax.set_prop_cycle("color", [plt.cm.summer(i) for i in np.linspace(0, 1, n_lines)]) | |
ax.stackplot(df.index.values, df.T, baseline="wiggle", labels=df.columns.values) | |
for s in ax.spines: | |
ax.spines[s].set_visible(False) | |
ax.yaxis.set_visible(False) | |
if legend: | |
ax.legend(loc="upper left") | |
plt.show() | |
def collect_messages(files): | |
chats = None | |
for f in files: | |
with open(f) as fp: | |
msgs = json.load(fp) | |
print(f) | |
try: | |
tmp = extract_msg_count(msgs) | |
except Exception as e: | |
print(e, f) | |
continue | |
if chats is None: | |
chats = tmp | |
else: | |
try: | |
chats = pd.concat([chats, tmp], axis=0, sort=True).fillna(0) | |
chats = chats.groupby(chats.index).sum() | |
except Exception as e: | |
print(e, tmp) | |
return chats | |
def main(): | |
files = glob.glob("**/message.json", recursive=True) | |
df = collect_messages(files) | |
df = aggregate(df) | |
stackplot_messages(df) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment