time_series_visualizer.py

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', index_col='date', parse_dates=['date'])

# Clean data - remove top 2.5% and bottom 2.5% data.
df = df[(df["value"] >= df["value"].quantile(0.025)) & (df["value"] <= df["value"].quantile(0.975))]

months_dict = {
    "01": "January",
    "02": "February",
    "03": "March",
    "04": "April",
    "05": "May",
    "06": "June",
    "07": "July",
    "08": "August",
    "09": "September",
    "10": "October",
    "11": "November",
    "12": "December"
}

months_list = months_dict.values()

def draw_line_plot():
    # Draw line plot
    fig = plt.figure(figsize=(16, 85))
    plt.plot(df, 'r')
    plt.title("Daily freeCodeCamp Forum Page Views 5/2016-12/2019")
    plt.xlabel("Date")
    plt.ylabel("Page Views")

    # Save image and return fig (don't change this part)
    fig.savefig('line_plot.png')
    return fig

def draw_bar_plot():
    bar_list = [[str(df.index[i]).split("-")[0], months_dict[str(df.index[i]).split("-")[1]], df["value"][i]] for i in range(len(df))]
    # Copy and modify data for monthly bar plot

    # Draw bar plot
    fig = plt.figure(figsize = (12, 12))
    df_bar = pd.DataFrame(bar_list, columns = ["Years", "Months", "Average Page Views"])
    sns.barplot(x="Years", y="Average Page Views", hue="Months", hue_order=months_list, data=df_bar, ci=0, saturation=1)

    # 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_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)
    # separate the months so they can be ordered
    df_box['month_num'] = df_box['date'].dt.month
    df_box = df_box.sort_values('month_num')

    # create both of the plots, grouped by particular date feature
    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(15,10))
    axes[0] = sns.boxplot(x=df_box['year'], y=df_box['value'], ax=axes[0])
    axes[1] = sns.boxplot(x=df_box['month'], y=df_box['value'], ax=axes[1])

    # set labels for the year
    axes[0].set_title("Year-wise Box Plot (Trend)")
    axes[0].set_xlabel("Year")
    axes[0].set_ylabel("Page Views")

    # set labels for the month
    axes[1].set_title("Month-wise Box Plot (Seasonality)")
    axes[1].set_xlabel("Month")
    axes[1].set_ylabel("Page Views")

    # Save image and return fig (don't change this part)
    fig.savefig('box_plot.png')
    return fig