tanpengshi

tanpengshi

tanpengshi

tanpengshi

df['ENTRY_DELTA'][df['ENTRY_DELTA']>10000]=np.nan
df['ENTRY_DELTA'][df['ENTRY_DELTA']<0]=np.nan
# Setting the anomaly values due to reset of counters to the uniform NaN values

delta_list = list(df['ENTRY_DELTA'])
ind = 0
for i in delta_list:
    if np.isnan(i) == 1:
        delta_list[ind] = np.nanmean([delta_list[ind-1],delta_list[ind+1]])
    ind += 1

tanpengshi

group_station = df.groupby('STATION')['ENTRY_EXIT'].sum().sort_values(ascending=False)

fig1 = plt.figure(figsize=[8,6])
ax1 = sns.distplot(group_station,bins=50,kde=False)
plt.xlim([0,410000])
plt.ylabel('No. of Stations',fontsize=15, weight='bold')
plt.xlabel('Total Traffic', fontsize=15, weight='bold')
ax1.annotate('Top 10 Stations', xy=(0.73, 0.08), xytext=(0.73, 0.12), xycoords='axes fraction', 
            fontsize=12, ha='center', va='bottom',
            arrowprops=dict(arrowstyle='-[, widthB=9.0, lengthB=1', lw=1.0),color='blue')

tanpengshi

plt.figure(figsize=[8,5])
ax = sns.barplot(data=group_station.head(10).reset_index(),x='ENTRY_EXIT',y='STATION',palette='rainbow')
plt.xlabel('Total Traffic',weight='bold',fontsize=15)
plt.ylabel('Top 10 Stations',weight='bold',fontsize=15)
plt.xticks(range(0,400001,50000),[str(int(i/1000))+'k' for i in range(0,400001,50000)])
plt.title('Busiest MTA Stations from 22/8 to 28/8', weight='bold',fontsize='15')
for p in ax.patches:
        ax.annotate(str(int(p.get_width()/1000))+'k', (p.get_width(), p.get_y()+0.5))
sns.despine()

tanpengshi

df_10 = df[df['STATION'].isin(list(group_station.head(10).index))]
df_10['WEEKDAY'] = df_10['DATE'].dt.day_name()
group_station_day = df_10.groupby(['STATION','WEEKDAY'])['ENTRY_EXIT'].sum()
matrix_station_day = group_station_day.unstack()
matrix_station_day.reset_index()
matrix_station_day = matrix_station_day.reindex(columns=["Monday","Tuesday","Wednesday","Thursday","Friday","Saturday","Sunday"])
matrix_station_day = matrix_station_day.reindex(index=list(group_station.head(10).index))

array = np.array(matrix_station_day.applymap(lambda x:str(round(x/1000,1))+'k'))
fig2 = plt.figure(figsize=[10,10])

tanpengshi

def timeperiod(time):
    if time >= datetime.time(0,0,0) and time < datetime.time(4,0,0):
        return "12am-4am"
    elif time >= datetime.time(4,0,0) and time < datetime.time(8,0,0):
        return "4am-8am"
    elif time >= datetime.time(8,0,0) and time < datetime.time(12,0,0):
        return "8am-12pm"
    elif time >= datetime.time(12,0,0) and time < datetime.time(16,0,0):
        return "12pm-4pm"    
    elif time >= datetime.time(16,0,0) and time < datetime.time(20,0,0):

tanpengshi

matrix_list= []
for station in list(group_station.head(10).index):
    df_station = df_10[df_10['STATION']==station]
    group_day_time = df_station.groupby(['WEEKDAY','TIME_PERIOD'])['ENTRY_EXIT'].sum()
    matrix_day_time = group_day_time.unstack()
    matrix_day_time.reset_index()   
    matrix_day_time = matrix_day_time.reindex(index=["Monday","Tuesday","Wednesday","Thursday","Friday","Saturday","Sunday"])
    matrix_day_time = matrix_day_time.reindex(columns=["12am-4am","4am-8am","8am-12pm","12pm-4pm","4pm-8pm","8pm-12am"])
    matrix_list.append(matrix_day_time)

tanpengshi

import numpy as np
from bs4 import BeautifulSoup
import requests

player_list = []
url = 'https://www.fifaindex.com/players/{}/'   #creating url for primary pages

pageno = 1

while True: