ajey091

speedbins = np.linspace(0,185,50)
speeddf2['speedbinned'] = pd.cut(speeddf2['SPEED'], speedbins)
speedbinsviol = speeddf2['speedbinned'].value_counts().sort_index()

speeddf2['new_column'] = speeddf2['LINK_POINTS'].apply(lambda x: x[0:18])
speeddf3 = pd.DataFrame(speeddf2['new_column'].str.split(',',1).tolist(),columns=['Lat','Long'])

speeddf2['Lat'] = speeddf3['Lat']
speeddf2['Long'] = speeddf3['Long']
speeddf4 = speeddf2.loc[speeddf2['SPEED']>65]

ajey091

speeddf = pd.read_csv('DOT_Traffic_Speeds_NBE.csv', index_col=False, header=0)
speeddf2 = speeddf.dropna()
print(speeddf2.head(3))

ajey091

df2['SpeedFlag'] = np.where(df2['Violation Description'].str.contains("speed", case=False, na=False), 1, 0)
df2['SpeedFlag'] = df2['SpeedFlag'].astype(bool)
speedingviol = df2[df2['SpeedFlag']==1]

ajey091

agebins = np.linspace(15,90,26)
df2['agebinned'] = pd.cut(df2['Age at Violation'], agebins)
violagebins = df2['agebinned'].value_counts().sort_index()


fig, ax = plt.subplots()
plt.rcParams["figure.figsize"] = (14,10)
violagebins.plot(ax=ax,kind='bar')
plt.xlabel('Age group')
plt.ylabel('Number of violations')

ajey091

violage = df2['Age at Violation'].value_counts().sort_index()
fig, ax = plt.subplots()
violage.plot(ax=ax,kind='bar')
plt.rcParams["figure.figsize"] = (14,10)
ticklabels = ['']*len(violage.index)
# Every 4th ticklable shows the month and day
ticklabels[::4] = [item for item in violage.index[::4]]
ax.xaxis.set_major_formatter(ticker.FixedFormatter(ticklabels))
plt.xlabel('Age at violation')
plt.ylabel('Number of violations')

ajey091

violday = df2['Violation Day of Week'].value_counts()
fig, ax = plt.subplots()

violday.plot(ax=ax,kind='bar')
plt.xlabel('Day of week')
plt.ylabel('Number of violations')
plt.show();

ajey091

violmonth = df2['Violation Month'].value_counts().sort_index()
fig, ax = plt.subplots()
violmonth.plot(ax=ax,kind='bar')
x1 = [0,1,2,3,4,5,6,7,8,9,10,11]
squad = ['January','February','March','April','May','June','July','August','September','October','November','December']

matplotlib.rcParams.update({'font.size': 22})
plt.rcParams["figure.figsize"] = (10,10)

ax.set_xticks(x1)

ajey091

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import matplotlib
import matplotlib.ticker as ticker
from matplotlib.cm import plasma
pd.options.mode.chained_assignment = None

df = pd.read_csv('Traffic_Tickets_Issued__Four_Year_Window.csv', index_col=False, header=0)
df2 = df.dropna()  # we ignore rows with incomplete data

ajey091

This is a test gist.