Parler Data Analysis

https://towardsdatascience.com/visualizing-geospatial-data-in-python-e070374fe621 https://mode.com/blog/python-data-visualization-libraries/

!mkdir data

!ls -n

total 24
-rw-r--r-- 1 1000 100 18504 Nov 13 21:01 change_detection.ipynb
drwxr-xr-x 2 1000 100    64 Feb 18 00:34 data
-rw-r--r-- 1 1000 100    72 Feb 18 00:33 parler_data.ipynb

!curl -LOk https://srv-store6.gofile.io/download/7Wg83o/parler-videos-geocoded.csv.zip > data/parler-videos-geocoded.csv.zip

  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100 1371k  100 1371k    0     0  71794      0  0:00:19  0:00:19 --:--:--  179k

!cd data;ls -n

total 3340
-rw-r--r-- 1 1000 100 3416205 Jan 12 05:54 parler-videos-geocoded.csv
-rw-r--r-- 1 1000 100       0 Feb 18 00:41 parler-videos-geocoded.csv.zip

import pandas as pd

df = pd.read_csv('data/parler-videos-geocoded.csv')

df.head(5)

df.dtypes

Longitude    float64
Latitude     float64
Timestamp     object
ID            object
dtype: object

df['Timestamp']=pd.to_datetime(df['Timestamp'])

df['Timestamp'].min()

Timestamp('2010-08-08 21:44:38')

df['Timestamp'].max()

Timestamp('2021-01-10 14:30:29')

def years(x):
    return x.strftime('%Y-%m')

df['YYYY-MM']=df['Timestamp'].apply(lambda x: years(x))

timeseries=pd.DataFrame(df.groupby('YYYY-MM').count()['ID'])
timeseries.tail(5)

# Parler launched September 2018
t = timeseries[timeseries.index>='2018-09']

t.plot()

<AxesSubplot:xlabel='YYYY-MM'>

import numpy as np
import matplotlib.pyplot as plt

plt.figure(figsize=(20, 12))

t2 = timeseries[timeseries.index>='2020-03']
# only one line may be specified; full height
# plt.axvline(x=36, color='b', label='axvline - full height')

# place legend outside
plt.legend(bbox_to_anchor=(1.0, 1), loc='upper left')
plt.plot(t2.index,t2['ID'])
plt.axvline(x='2020-11', color='r', label='axvline - partial height',ls='--')
plt.show()

No handles with labels found to put in legend.

# adding back day to chart out twitter suspensions
def days(x):
    return x.strftime('%Y-%m-%d')

df['day']=df['Timestamp'].apply(lambda x: days(x))
t2 = pd.DataFrame(df.groupby('day').count()['ID'])
t2 = t2[t2.index>='2020-10']

t2[t2.index>'2020-01-01']

from matplotlib.dates import DateFormatter
t2

plt.figure(figsize=(20, 12))
plt.legend(bbox_to_anchor=(1.0, 1), loc='upper left')
plt.plot(t2.index,t2['ID'])
plt.axvline(x='2020-11-04', color='r', label='axvline - partial height',ls='--')
# plt.xticks(rotation=17,3)
plt.show()

No handles with labels found to put in legend.

plt.figure(figsize=(10, 7))

t2 = timeseries[timeseries.index>='2020-03']
# only one line may be specified; full height
# plt.axvline(x=36, color='b', label='axvline - full height')

# place legend outside
plt.legend(bbox_to_anchor=(1.0, 1), loc='upper left')
plt.plot(t2.index,t2['ID'])
plt.axvline(x='2020-11', color='r', label='axvline - partial height',ls='--')
plt.show()

import numpy as np

import matplotlib.image as mpimg
from mpl_toolkits.basemap import Basemap

fig, ax = plt.subplots()
earth = Basemap(ax=ax)
earth.drawcoastlines(color='#556655', linewidth=0.5)
ax.scatter(df['Longitude'],df['Latitude'],c='blue',alpha=0.1)

<matplotlib.collections.PathCollection at 0x7f7384bd3460>

# Make the figure
fig = plt.figure()
ax = fig.add_subplot(111)

# Map of Washington, DC
bot_left_lat  =38.808277
bot_left_lon  =-76.914339
top_right_lat =38.978921
top_right_lon = -77.140698

# create the map object, m
m = Basemap(resolution='f', projection='cyl', \
    llcrnrlon=bot_left_lon, llcrnrlat=bot_left_lat, \
            urcrnrlon=top_right_lon, urcrnrlat=top_right_lat,ax=ax)

m.drawstates()
ax.scatter(df['Longitude'],df['Latitude'],c='blue',alpha=0.1)

<matplotlib.collections.PathCollection at 0x7f7385005f10>

dc area

top,left = [38.978921, -77.140698] bottom,right = [38.808277, -76.914339]

Not very interesting

import conda
import os

conda_file_dir = conda.__file__
conda_dir = conda_file_dir.split('lib')[0]
proj_lib = os.path.join(os.path.join(conda_dir, 'share'), 'proj')
os.environ["PROJ_LIB"] = proj_lib