Analyzing River Thames Water Levels
Time series data is everywhere, from watching your stock portfolio to monitoring climate change, and even live-tracking as local cases of a virus become a global pandemic. In this project, you’ll work with a time series that tracks the tide levels of the Thames River. You’ll first load the data and inspect it data visually, and then perform calculations on the dataset to generate some summary statistics. You’ll end by decomposing the time series into its component attributes and analyzing them.
The original dataset is available from the British Oceanographic Data Center here and you can read all about this fascinating archival story in this article from the Nature journal.
Here's a map of the locations of the tidal gauges along the River Thames in London.
The dataset comes with a file called Data_description.pdf. The dataset consists of 13 .txt files, containing comma separated data. We'll begin by analyzing one of them, the London Bridge gauge, and preparing it for analysis. The same code can be used to analyze data from other files (i.e. other gauges along the river) later.
| Variable Name | Description | Format |
|---|---|---|
| Date and time | Date and time of measurement to GMT. Note the tide gauge is accurate to one minute. | dd/mm/yyyy hh:mm:ss |
| Water level | High or low water level measured by tide gauge. Tide gauges are accurate to 1 centimetre. | metres (Admiralty Chart Datum (CD), Ordnance Datum Newlyn (ODN or Trinity High Water (THW)) |
| Flag | High water flag = 1, low water flag = 0 | Categorical (0 or 1) |
# We've imported your first Python package for you, along with a function you will need called IQR
import pandas as pd
def IQR(column):
q25, q75 = column.quantile([0.25, 0.75])
return q75-q25# load the London Bridge data
lb = pd.read_csv('data/10-11_London_Bridge.txt', sep=',')
lb.columns = ['datetime', 'water_level', 'is_high_tide', 'hw_lw']
df = lb.iloc[:,:3]
print(df.head())print(df.dtypes)df.datetime = pd.to_datetime(df.datetime)
df.water_level = df.water_level.astype(float)
df['month'] = df['datetime'].dt.month
df['year'] = df['datetime'].dt.year
df.head()tide_high = df[df.is_high_tide == 1]['water_level']
tide_low = df[df.is_high_tide == 0]['water_level']
# Using tide_high and tide_low, create two dictionaries, high_statistics and low_statistics, containing the mean, median, and IQR of each variable respectively, using the .agg() function from pandas and the IQR function provided.
high_statistics = tide_high.agg(['mean', 'median', IQR])
low_statistics = tide_low.agg(['mean', 'median', IQR])
Return a pandas Series that counts the number of days of high tide data you have per year in df and store it as all_high_days. Return a pandas Series that counts the number of days of data where water level was above the 75th percentile in df. Return a variable called high_ratio, which computes the ratio of high_days to all_high_days.
Return your solution as a dictionary with the keys high_statistics, low_statistics, high_ratio, and low_ratio. Use the variables you have already generated as values for each of these keys.
# Filter df for high and low tide
# tide_high = df.query('is_high_tide==1')['water_level']
# tide_low = df.query('is_high_tide==0')['water_level']
tide_high = df[df.is_high_tide == 1]['water_level']
tide_low = df[df.is_high_tide == 0]['water_level']
high_statistics = tide_high.agg(['mean', 'median', IQR])
low_statistics = tide_low.agg(['mean', 'median', IQR])
all_high_days = df.query('is_high_tide==1').groupby('year').count()['water_level']
high_days = df.query(f'(water_level>{tide_high.quantile(.75)}) & (is_high_tide==1)').groupby('year').count()['water_level']
high_ratio = (high_days/all_high_days).reset_index()
all_low_days = df.query('is_high_tide==0').groupby('year').count()['water_level']
low_days = df.query(f'(water_level<{tide_low.quantile(.25)}) & (is_high_tide==0)').groupby('year').count()['water_level']
low_ratio = (low_days/all_low_days).reset_index()
solution = {'high_statistics': high_statistics, 'low_statistics': low_statistics, 'high_ratio': high_ratio, 'low_ratio':low_ratio}
print(solution)