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")
df = df.set_index("date")

# 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, ax = plt.subplots(figsize=(10, 4))
    x = df.index
    y = df["value"]
    plt.plot(x, y, color="red")
    plt.xlabel("Date")
    plt.ylabel("Page Views")
    plt.title("Daily freeCodeCamp Forum Page Views 5/2016-12/2019")
    plt.xticks(x[::(len(x)//7)])
    
  




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

def draw_bar_plot():
    # Copy and modify data for monthly bar plot
    df_bar = df.copy()
    df_bar.index = pd.to_datetime(df_bar.index)
    df_bar["Years"] = df_bar.index.year
    df_bar["Months"] = df_bar.index.month_name()
    df_bar = pd.DataFrame(df_bar.groupby(["Years", "Months"], sort=False)["value"].mean().round().astype(int))
    df_bar = df_bar.rename(columns={"value" : "Average Page Views"})
    cat = {"Years" : [2016, 2016, 2016, 2016], "Months": ["January", "February", "March", "April"], "Avarage Page Views" : [0, 0, 0, 0]}
    df_bar = df_bar.reset_index()
    df_bar = pd.concat([pd.DataFrame(cat), df_bar])
    df_bar_pivot = df_bar.pivot(index="Years", columns="Months", values="Average Page Views")
    df_bar_pivot = df_bar_pivot.reindex(df_bar["Months"][:12], axis=1)
    fig = df_bar_pivot.plot(kind="bar", figsize=(10, 5))
    plt.xlabel("Years")
    plt.ylabel("Average Page Views")
    fig = fig.figure  
    # Draw bar plot





    # 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.index = pd.to_datetime(df_box.index)
    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]
    df_box["num"] = df_box["date"].dt.month
    df_box = df_box.sort_values("num")      

    # Draw box plots (using Seaborn)
    fig, axes = plt.subplots(1, 2, figsize=(15, 7))
    axes[0] = sns.boxplot(x=df_box["year"], y=df_box["value"], ax=axes[0])
    axes[0].set_title("Year-wise Box Plot (Trend)") 
    axes[0].set_xlabel('Year')
    axes[0].set_ylabel('Page Views')
    axes[1] = sns.boxplot(x=df_box["month"], y=df_box["value"], ax=axes[1])
    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