Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
DataProject/1bweek.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
54 lines (45 sloc)
2.39 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import numpy as np | |
import pandas as pd | |
from IPython.display import display | |
from dask import dataframe as dd | |
import dask.dataframe as dd | |
import dask.array as da | |
import dask.bag as db | |
# Graph visualisation does not work without this. | |
import matplotlib | |
matplotlib.use('Agg') # Use the Agg backend | |
import matplotlib.pyplot as plt | |
from matplotlib.ticker import MaxNLocator | |
import matplotlib.dates as mdates | |
from datetime import datetime | |
from pandas.plotting import register_matplotlib_converters | |
register_matplotlib_converters() | |
# Load the CSV file using Dask | |
ddd = dd.read_csv('Trips_by_Distance.csv', usecols=['Week', 'Number of Trips 10-25', 'Number of Trips 50-100'], dtype={'Number of Trips 10-25': 'float64', 'Number of Trips 50-100' : 'float64'}) | |
# Trips 10-25 | |
grouped_ddd = ddd.groupby('Week') | |
combined_ddd = grouped_ddd['Number of Trips 10-25'].sum().reset_index() # Combining duplicate weeks | |
# Identify the weeks that > 10000000 people conducted 10-25 Number of Trips and compare them to > 10000000 people who did 50-100 Number of trips | |
popfilter = combined_ddd[combined_ddd['Number of Trips 10-25'] > 100000000] # Filter by weeks greater than 10000000 | |
weeks_list = popfilter['Week'].to_dask_array().compute().tolist() # Put the weeks into a list for easier plotting | |
# No need to convert to datetime because it's already numeric | |
# Plot the scatter plot | |
plt.scatter(x=weeks_list, y=popfilter["Number of Trips 10-25"].to_dask_array(lengths=True).compute()) | |
plt.title('Scatter plot of weeks where > 10000000 people conducted 10-25 number of trips') | |
plt.xlabel('Week') | |
plt.ylabel('Number of Trips 10-25') | |
plt.savefig('scatter1.png') | |
# Trips 50-100 | |
grouped_ddd_50_100 = ddd.groupby('Week') | |
combined_ddd_50_100 = grouped_ddd_50_100['Number of Trips 50-100'].sum().reset_index() | |
# Identify the weeks that > 10000000 people conducted 50-100 Number of Trips | |
popfilter_50_100 = combined_ddd_50_100[combined_ddd_50_100['Number of Trips 50-100'] > 10000000] | |
weeks_list_50_100 = popfilter_50_100['Week'].to_dask_array().compute().tolist() | |
# No need to convert to datetime because it's already numeric | |
# Plot the scatter plot for Trips 50-100 | |
plt.scatter(x=weeks_list_50_100, y=popfilter_50_100["Number of Trips 50-100"].to_dask_array(lengths=True).compute()) | |
plt.title('Scatter plot of weeks where > 10000000 people conducted 50-100 number of trips') | |
plt.xlabel('Week') | |
plt.ylabel('Number of Trips 50-100') | |
plt.savefig('scatter2.png') |