Page View Time Series Visualizer (test_data_cleaning error, test_box_plot_labels fail)

Python
1

I am having this error and can’t find the solution. Does anyone knows how to fix it? Thanks in advance.

...F...E...
======================================================================
ERROR: test_data_cleaning (test_module.DataCleaningTestCase)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/runner/boilerplate-page-view-time-series-visualizer/test_module.py", line 7, in test_data_cleaning
    actual = int(time_series_visualizer.df.count(numeric_only=True))
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/pandas/core/series.py", line 129, in wrapper
    raise TypeError(f"cannot convert the series to {converter}")
TypeError: cannot convert the series to <class 'int'>

and

FAIL: test_box_plot_labels (test_module.BoxPlotTestCase)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/runner/boilerplate-page-view-time-series-visualizer/test_module.py", line 99, in test_box_plot_labels
    self.assertEqual(actual, expected, "Expected box plot 2 secondary labels to be 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'")
AssertionError: Lists differ: ['May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', [36 chars]Apr'] != ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', [36 chars]Dec']

First differing element 0:
'May'
'Jan'

+ ['Jan',
+  'Feb',
+  'Mar',
+  'Apr',
- ['May',
? ^

+  'May',
? ^

   'Jun',
   'Jul',
   'Aug',
   'Sep',
   'Oct',
   'Nov',
-  'Dec',
?       ^

+  'Dec']
?       ^

-  'Jan',
-  'Feb',
-  'Mar',
-  'Apr'] : Expected box plot 2 secondary labels to be 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'

CODE:

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.date = pd.to_datetime(df.date)

df = df[(df.value >= (df.value.quantile(0.025))) & (df.value <= (df.value.quantile(0.975)))]


def draw_line_plot():
    plt.figure(figsize=(14,6))
    plt.title('Daily freeCodeCamp Forum Page Views 5/2016-12/2019')
    fig = sns.lineplot(data=df, x='date', y='value').figure
    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():
    # Copy and modify data for monthly bar plot
    df_bar = pd.DataFrame(df)
    df_bar['Year'] = df['date'].dt.year
    df_bar['Month'] = df['date'].dt.month
    df_bar_ave = df_bar.groupby(['Year', 'Month']).mean().unstack()
    months = ['January', 'February', 'March', 'April' , 'May' , 'June', 'July', 'August', 'September', 'October', 'November', 'December']

    # Draw bar plot

    fig = df_bar_ave.plot(kind ="bar", figsize=(15,5)).figure
    #plt.title("Average daily page views, by Month")
    plt.xlabel("Years")
    plt.ylabel("Average Page Views")
    plt.legend(fontsize =10, labels=months)


    # 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 = pd.DataFrame(df)
    df_box['Year'] = df['date'].dt.year
    df_box['Month'] = df['date'].dt.month
    df_box.loc[df_box['Month'] == 1, 'Month'] = "Jan"
    df_box.loc[df_box['Month'] == 2, 'Month'] = "Feb"
    df_box.loc[df_box['Month'] == 3, 'Month'] = "Mar"
    df_box.loc[df_box['Month'] == 4, 'Month'] = "Apr"
    df_box.loc[df_box['Month'] == 5, 'Month'] = "May"
    df_box.loc[df_box['Month'] == 6, 'Month'] = "Jun"
    df_box.loc[df_box['Month'] == 7, 'Month'] = "Jul"
    df_box.loc[df_box['Month'] == 8, 'Month'] = "Aug"
    df_box.loc[df_box['Month'] == 9, 'Month'] = "Sep"
    df_box.loc[df_box['Month'] == 10, 'Month'] = "Oct"
    df_box.loc[df_box['Month'] == 11, 'Month'] = "Nov"
    df_box.loc[df_box['Month'] == 12, 'Month'] = "Dec"


    # Draw box plots (using Seaborn)
    fig, axes = plt.subplots(figsize=(20, 5), ncols=2, sharex=False)
    sns.despine(left=True)

    box_plot_year = sns.boxplot(x=df_box['Year'], y=df_box.value, ax=axes[0])
    box_plot_year.set_title("Year-wise Box Plot (Trend)")
    box_plot_year.set_xlabel('Year')
    box_plot_year.set_ylabel('Page Views')

    box_plot_month = sns.boxplot(x=df_box['Month'], y=df_box.value, ax=axes[1])
    box_plot_month.set_title("Month-wise Box Plot (Seasonality)")
    box_plot_month.set_xlabel('Month')
    box_plot_month.set_ylabel('Page Views')   
    
    # Save image and return fig (don't change this part)
    fig.savefig('box_plot.png')
    return fig

Thank you!

2

FAIL: test_box_plot_labels (test_module.BoxPlotTestCase) -----the months need to be sorted(starting with Jan…Dec)