You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
114 lines
3.3 KiB
Python
114 lines
3.3 KiB
Python
import calendar
|
|
|
|
import matplotlib.pyplot as plt
|
|
import pandas as pd
|
|
import seaborn as sns
|
|
from pandas.plotting import register_matplotlib_converters
|
|
|
|
register_matplotlib_converters()
|
|
|
|
# Import data (Make sure to parse dates. Consider setting index column to 'date'.)
|
|
df = pd.read_csv("fcc-forum-pageviews.csv")
|
|
|
|
# Clean data
|
|
df = df[(
|
|
df['value'] >= df['value'].quantile(0.025))
|
|
& (df['value'] <= df['value'].quantile(0.975))]
|
|
|
|
|
|
def draw_line_plot():
|
|
# Draw line plot
|
|
fig, axs = plt.subplots(ncols=1, figsize=(20, 10))
|
|
sns.lineplot(df["value"], estimator=None).set(
|
|
xlabel="Date",
|
|
ylabel="Page Views",
|
|
xticklabels=df.index,
|
|
title='Daily freeCodeCamp Forum Page Views 5/2016-12/2019')
|
|
|
|
# Save image and return fig (don't change this part)
|
|
fig.savefig('line_plot.png')
|
|
return fig
|
|
|
|
|
|
def draw_bar_plot():
|
|
df = pd.read_csv(
|
|
"fcc-forum-pageviews.csv", parse_dates=True, index_col=[0])
|
|
df = df[
|
|
(df['value'] >= df['value'].quantile(0.025))
|
|
& (df['value'] <= df['value'].quantile(0.975))]
|
|
# Copy and modify data for monthly bar plot
|
|
df['year'] = df.index.year
|
|
df['month'] = df.index.month
|
|
|
|
# Draw bar plot
|
|
df.groupby(['year', 'month']).mean()
|
|
df_bar = df.groupby([df.index.year, df.index.month]).mean()
|
|
df_bar['month'] = df_bar['month'].apply(
|
|
lambda x: calendar.month_name[int(x)])
|
|
df_bar = df_bar.astype({'year': 'int'})
|
|
fig, axs = plt.subplots(ncols=1, figsize=(20, 10))
|
|
sns.barplot(
|
|
data=df_bar,
|
|
x='year',
|
|
y='value',
|
|
hue='month',
|
|
hue_order=[
|
|
'January',
|
|
'February',
|
|
'March',
|
|
'April',
|
|
'May',
|
|
'June',
|
|
'July',
|
|
'August',
|
|
'September',
|
|
'October',
|
|
'November',
|
|
'December']).set(
|
|
xlabel='Years', ylabel='Average Page Views')
|
|
|
|
# Save image and return fig (don't change this part)
|
|
fig.savefig('bar_plot.png')
|
|
return fig
|
|
|
|
|
|
def draw_box_plot():
|
|
# Prepare data for box plots (this part is done!)
|
|
df = pd.read_csv("fcc-forum-pageviews.csv", parse_dates=True, index_col=0)
|
|
df = df[(df['value'] >= df['value'].quantile(0.025))
|
|
& (df['value'] <= df['value'].quantile(0.975))]
|
|
df_box = df.copy()
|
|
df_box.reset_index(inplace=True)
|
|
df_box['year'] = [d.year for d in df_box.date]
|
|
df_box['month'] = [d.strftime('%b') for d in df_box.date]
|
|
|
|
# Draw box plots (using Seaborn)
|
|
fig, axs = plt.subplots(ncols=2, figsize=(24, 10))
|
|
sns.boxplot(data=df_box, ax=axs[0], x="year", y="value").set(
|
|
title="Year-wise Box Plot (Trend)", ylabel="Page Views", xlabel="Year")
|
|
sns.boxplot(
|
|
data=df_box,
|
|
ax=axs[1],
|
|
x="month",
|
|
y="value",
|
|
order=[
|
|
"Jan",
|
|
"Feb",
|
|
"Mar",
|
|
"Apr",
|
|
"May",
|
|
"Jun",
|
|
"Jul",
|
|
"Aug",
|
|
"Sep",
|
|
"Oct",
|
|
"Nov",
|
|
"Dec"]).set(
|
|
title="Month-wise Box Plot (Seasonality)",
|
|
ylabel="Page Views",
|
|
xlabel="Month")
|
|
|
|
# Save image and return fig (don't change this part)
|
|
fig.savefig('box_plot.png')
|
|
return fig
|