Using Python for Research_Case Study 5

00_notes.txt

"""
np.isnan()
查看是否有nan

np.isnan(speed).any()
是true的話代表一定有nan值

np.sum(np.isnan())
看有幾個nan的值

~對pd.Series和pd.DaraFrame可以轉換true與false

datetime.datetime.strptime(data,"%Y-%m-%d %H:%M:%S") 將時間以 年(西元) 月 日 時(24hr) 分 秒 去處理

plt.hist有NAN值會error
 
有很酷的cartopy工具
"""

01_3traj.py

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import datetime
birddata=pd.read_csv("bird_tracking.csv")

#可以觀察data的詳細資料
birddata.info()

bird_names=birddata.bird_name.unique()
plt.figure(figsize=(7,7))
for birdname in bird_names:
    ix=birddata.bird_name == birdname
    x,y=birddata.longitude[ix] , birddata.latitude[ix]
    plt.plot(x,y,'.',label=birdname)
plt.xlabel('Longitude')
plt.ylabel('Latitude')
plt.legend(loc="lower right")

plt.savefig("3traj.png")

02_hist.py

plt.figure(figsize=(8,4))
speed=birddata.speed_2d[birddata.bird_name=='Eric']
ind=np.isnan(speed)
#只畫有數值的，並且normalize，讓frequency總和為1
#注意用plt.hist方式畫畫時，要考慮NAN值
plt.hist(speed[~ind],bins=np.linspace(0,30,30),normed=True) # ~ 對pd.Series和pd.DaraFrame可以轉換true與false
plt.axis('tight')
plt.xlabel('2D speed(m/s)')
plt.ylabel('Frequency');
plt.savefig("hist.png")


##這裡帶到也可以用pandas畫畫，且沒有NAN值的限制
##birddata.speed_2d.plot(kind='hist',range=[0,30])
##plt.xlabel('2D speed')
##plt.show()

03_timestamps.py

timestamps=[]
#datetime.datetime.strptime(data,"%Y-%m-%d %H:%M:%S") 將時間以 年(西元) 月 日 時(24hr) 分 秒 去處理
#在這裡消除原始資料中 +00 的值
for k in range(len(birddata)):
    timestamps.append(datetime.datetime.strptime(birddata.date_time[k][:-3],"%Y-%m-%d %H:%M:%S"))

    
birddata["timestamp"] = pd.Series(timestamps, index=birddata.index)

data=birddata[birddata.bird_name=="Eric"]
times=data.timestamp
elapsed_time=[time-times[0] for time in times] #算出和第一個相差時間
elapsed_days=np.array(elapsed_time)/datetime.timedelta(days=1) #相差時間換算成天數、小時用hours=1

plt.plot(elapsed_days)
plt.xlabel("Obeservation")
plt.ylabel("Elapsed time (days)");
plt.savefig('timeplot.png')

04_day.py

#將同一天的紀錄取平均畫出來
nextday=1
inds=[]
daily_mean_speed=[]
for (i,k) in enumerate(elapsed_days):
    if k<nextday:
        inds.append(i)
    else:
        daily_mean_speed.append(np.mean(data.speed_2d[inds]))
        nextday+=1
        inds=[]

plt.figure(figsize=(8,6))
plt.plot(daily_mean_speed)
plt.xlabel('Day')
plt.ylabel('Mean speed (m/s)');
plt.savefig('dms.png')

05_cartopy.py

import cartopy.crs as ccrs
import cartopy.feature as cfeature

proj=ccrs.Mercator()

plt.figure(figsize=(10,10))
ax=plt.axes(projection=proj)
ax.set_extent((-25.0,20.0,52.0,10.0))

ax.add_feature(cfeature.LAND)
ax.add_feature(cfeature.OCEAN)
ax.add_feature(cfeature.COASTLINE)
ax.add_feature(cfeature.BORDERS, linestyle=':')

for name in bird_names:
    ix=birddata['bird_name']==name
    x,y = birddata.longitude[ix],birddata.latitude[ix]
    ax.plot(x,y,'.',transform=ccrs.Geodetic(),label=name)

plt.legend(loc="upper left")
plt.savefig("map.png")

06_hw.py

# First, use `groupby()` to group the data by "bird_name".
grouped_birds =birddata.groupby('bird_name')

# Now calculate the mean of `speed_2d` using the `mean()` function.
mean_speeds = grouped_birds['speed_2d'].mean()

# Use the `head()` method prints the first 5 lines of each bird.
grouped_birds.head()

# Find the mean `altitude` for each bird.
mean_altitudes = grouped_birds['altitude'].mean()

# Convert birddata.date_time to the `pd.datetime` format.
birddata.date_time = pd.to_datetime(birddata.date_time) 

# Create a new column of day of observation
birddata["date"] = birddata.date_time.dt.date #只抓日期

# Check the head of the column.
birddata["date"].head()

# Use `groupby()` to group the data by date.
grouped_bydates = birddata.groupby('date')

# Find the mean `altitude` for each date.
mean_altitudes_perday =grouped_bydates.altitude.mean()

# Use `groupby()` to group the data by bird and date.
grouped_birdday = birddata.groupby(['bird_name','date'])

# Find the mean `altitude` for each bird and date.
mean_altitudes_perday =grouped_birdday.altitude.mean()

# look at the head of `mean_altitudes_perday`.
mean_altitudes_perday.head()

#自己重新的另外一個寫法
#eric_daily_speed  = birddata[birddata.bird_name=='Eric'].groupby('date').speed_2d.mean()
#sanne_daily_speed = birddata[birddata.bird_name=='Sanne'].groupby('date').speed_2d.mean()
#nico_daily_speed  = birddata[birddata.bird_name=='Nico'].groupby('date').speed_2d.mean()

eric_daily_speed  = grouped_birdday.speed_2d.mean()["Eric"]
sanne_daily_speed = grouped_birdday.speed_2d.mean()["Sanne"]
nico_daily_speed  = grouped_birdday.speed_2d.mean()["Nico"]


plt.plot(eric_daily_speed,label="Eric")
plt.plot(sanne_daily_speed,label="Sanne")
plt.plot(nico_daily_speed,label="Nico")
plt.xticks(fontsize=8)
plt.legend(loc="upper left")
plt.savefig('speed of each bird per day')