Solution

Signed-off-by: Prince Mendiratta <prince.mendi@gmail.com>

Signed-off-by: Prince Mendiratta <prince.mendi@gmail.com>

README.md

@@ -1,24 +1,3 @@
-### Assignment
+# Page View Time Series Visualizer
 
-For this project you will visualize time series data using a line chart, bar chart, and box plots. You will use Pandas, Matplotlib, and Seaborn to visualize a dataset containing the number of page views each day on the freeCodeCamp.org forum from 2016-05-09 to 2019-12-03. The data visualizations will help you understand the patterns in visits and identify yearly and monthly growth.
-
-Use the data to complete the following tasks:
-* Use Pandas to import the data from "fcc-forum-pageviews.csv". Set the index to the "date" column.
-* Clean the data by filtering out days when the page views were in the top 2.5% of the dataset or bottom 2.5% of the dataset.
-* Create a `draw_line_plot` function that uses Matplotlib to draw a line chart similar to "examples/Figure_1.png". The title should be "Daily freeCodeCamp Forum Page Views 5/2016-12/2019". The label on the x axis should be "Date" and the label on the y axis should be "Page Views".
-* Create a `draw_bar_plot` function that draws a bar chart similar to "examples/Figure_2.png". It should show average daily page views for each month grouped by year. The legend should show month labels and have a title of "Months". On the chart, the label on the x axis should be "Years" and the label on the y axis should be "Average Page Views".
-* Create a `draw_box_plot` function that uses Searborn to draw two adjacent box plots similar to "examples/Figure_3.png". These box plots should show how the values are distributed within a given year or month and how it compares over time. The title of the first chart should be "Year-wise Box Plot (Trend)" and the title of the second chart should be "Month-wise Box Plot (Seasonality)". Make sure the month labels on bottom start at "Jan" and the x and x axis are labeled correctly.
-
-For each chart, make sure to use a copy of the data frame. Unit tests are written for you under `test_module.py`.
-
-### Development
-
-For development, you can use `main.py` to test your functions. Click the "run" button and `main.py` will run.
-
-### Testing 
-
-We imported the tests from `test_module.py` to `main.py` for your convenience. The tests will run automatically whenever you hit the "run" button.
-
-### Submitting
-
-Copy your project's URL and submit it to freeCodeCamp.
+This is the boilerplate for the Page View Time Series Visualizer project. Instructions for building your project can be found at https://www.freecodecamp.org/learn/data-analysis-with-python/data-analysis-with-python-projects/page-view-time-series-visualizer

pyproject.toml

@@ -3,6 +3,8 @@
 authors = ["Your Name <you@example.com>"]
 name = "root"
 version = "0.0.0"
+description = ""
+
 [tool.poetry.dependencies]
 pandas = "*"
 python = "^3.7"

test_module.py

@@ -4,7 +4,7 @@ import matplotlib as mpl
 
 class DataCleaningTestCase(unittest.TestCase):
     def test_data_cleaning(self):
-        actual = int(time_series_visualizer.df.count())
+        actual = int(time_series_visualizer.df.count(numeric_only=True))
         expected = 1238
         self.assertEqual(actual, expected, "Expected DataFrame count after cleaning to be 1238.")
 
@@ -26,7 +26,7 @@ class LinePlotTestCase(unittest.TestCase):
         expected = "Page Views"
         self.assertEqual(actual, expected, "Expected line plot ylabel to be 'Page Views'")
 
-    def test_line_plot_data_quatity(self):
+    def test_line_plot_data_quantity(self):
         actual = len(self.ax.lines[0].get_ydata())
         expected = 1238
         self.assertEqual(actual, expected, "Expected number of data points in line plot to be 1238.")
@@ -83,10 +83,10 @@ class BoxPlotTestCase(unittest.TestCase):
         self.assertEqual(actual, expected, "Expected box plot 1 ylabel to be 'Page Views'")
         actual = self.ax2.get_xlabel()
         expected = "Month"
-        self.assertEqual(actual, expected, "Expected box plot 1 xlabel to be 'Month'")
+        self.assertEqual(actual, expected, "Expected box plot 2 xlabel to be 'Month'")
         actual = self.ax2.get_ylabel()
         expected = "Page Views"
-        self.assertEqual(actual, expected, "Expected box plot 1 ylabel to be 'Page Views'")
+        self.assertEqual(actual, expected, "Expected box plot 2 ylabel to be 'Page Views'")
         actual = []
         for label in self.ax1.get_xaxis().get_majorticklabels():
             actual.append(label.get_text())
@@ -109,9 +109,9 @@ class BoxPlotTestCase(unittest.TestCase):
         self.assertEqual(actual, expected, "Expected box plot 1 title to be 'Year-wise Box Plot (Trend)'")
         actual = self.ax2.get_title()
         expected = "Month-wise Box Plot (Seasonality)"
-        self.assertEqual(actual, expected, "Expected box plot 1 title to be 'Month-wise Box Plot (Seasonality)'")
+        self.assertEqual(actual, expected, "Expected box plot 2 title to be 'Month-wise Box Plot (Seasonality)'")
 
-    def test_box_plot_number_of_boxs(self):
+    def test_box_plot_number_of_boxes(self):
         actual = len(self.ax1.lines) / 6 # Every box has 6 lines
         expected = 4
         self.assertEqual(actual, expected, "Expected four boxes in box plot 1")

time_series_visualizer.py

@@ -1,53 +1,112 @@
+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 = None
+df = pd.read_csv("fcc-forum-pageviews.csv")
 
 # Clean data
-df = None
+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_bar = None
+    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')