Why time-based analysis reveals trends in Data Analysis Python - Challenge Your Understanding

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this time series rolling mean calculation?

Given a time series data, what is the output of the rolling mean calculation shown below?

Data Analysis Python

import pandas as pd

data = pd.Series([10, 20, 30, 40, 50], index=pd.date_range('2024-01-01', periods=5))
rolling_mean = data.rolling(window=3).mean()
print(rolling_mean.tolist())

A [nan, nan, 20.0, 30.0, 40.0]

B [10.0, 15.0, 20.0, 30.0, 40.0]

C [nan, 15.0, 20.0, 30.0, 40.0]

D [10.0, 20.0, 30.0, 40.0, 50.0]

💡 Hint

Remember, rolling mean with window=3 needs 3 values to compute the first mean.

The rolling mean with window size 3 returns NaN for the first two values because there are not enough data points to calculate the mean. Starting from the third value, it calculates the mean of the current and previous two values.

❓ data_output

intermediate

How many peaks are detected in this time series data?

Using the following time series data, how many peaks are detected by the code?

Data Analysis Python

import numpy as np
from scipy.signal import find_peaks

data = np.array([1, 3, 7, 1, 2, 6, 0, 1])
peaks, _ = find_peaks(data)
print(len(peaks))

A 2

B 1

C 4

D 3

💡 Hint

Peaks are points higher than their neighbors.

The peaks are at indices 2 (value 7), 5 (value 6), and 7 (value 1, which is higher than its left neighbor 0). Total of 3 peaks.

❓ visualization

advanced

Which plot shows a clear upward trend over time?

Given these four plots of time series data, which one clearly shows an upward trend?

Data Analysis Python

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

dates = pd.date_range('2024-01-01', periods=50)
data1 = pd.Series(np.random.normal(0, 1, 50), index=dates)
data2 = pd.Series(np.linspace(0, 10, 50) + np.random.normal(0, 1, 50), index=dates)
data3 = pd.Series(np.sin(np.linspace(0, 10, 50)), index=dates)
data4 = pd.Series(np.random.normal(5, 1, 50), index=dates)

plt.figure(figsize=(10, 6))
plt.subplot(2, 2, 1)
plt.plot(data1)
plt.title('A')

plt.subplot(2, 2, 2)
plt.plot(data2)
plt.title('B')

plt.subplot(2, 2, 3)
plt.plot(data3)
plt.title('C')

plt.subplot(2, 2, 4)
plt.plot(data4)
plt.title('D')

plt.tight_layout()
plt.show()

A Plot B

B Plot D

C Plot C

D Plot A

💡 Hint

Look for a steady increase in values over time.

Plot B shows a line with a positive slope plus some noise, indicating an upward trend. Others show noise, oscillation, or no clear trend.

🔧 Debug

advanced

What error does this time series resampling code produce?

What error will this code raise when trying to resample a time series?

Data Analysis Python

import pandas as pd

data = pd.Series([1, 2, 3], index=[1, 2, 3])
resampled = data.resample('D').mean()
print(resampled)

A ValueError: Invalid frequency string

B AttributeError: 'Series' object has no attribute 'resample'

C TypeError: Only valid with DatetimeIndex, TimedeltaIndex or PeriodIndex, but got an instance of 'Int64Index'

D No error, prints resampled data

💡 Hint

Check the index type required for resampling.

Resampling requires a time-based index like DatetimeIndex. Here the index is integers, so it raises a TypeError.

🚀 Application

expert

Which method best reveals seasonal trends in monthly sales data?

You have monthly sales data for 5 years. Which method best reveals seasonal trends?

A Calculate daily differences between sales values

B Calculate a 12-month rolling average to smooth data

C Plot histogram of sales values

D Use linear regression on raw monthly sales

💡 Hint

Seasonal trends repeat every year, so smoothing over 12 months helps.

A 12-month rolling average smooths out short-term fluctuations and highlights yearly seasonal patterns. Linear regression fits a trend but misses seasonality. Histogram shows distribution, not time trends. Daily differences are irrelevant for monthly data.