🚩 Some of the graphs in this notebook are interactive, don't forget to click around :) 📢¶
Hector Ramirez
ramirez.gomez.hector@gmail.com
Libraries¶
In [1]:
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.offline as py_offline
import matplotlib.pyplot as plt
import scipy.stats as stats
Task A¶
Read & Explore Data¶
In [2]:
df_a = pd.read_excel('Take Home Technical Screen.xlsx', sheet_name='Task A') # Read Task A data
df_a.head()
Out[2]:
| Product | Month ID (YYYYMM) | Defects | Opportunities | Defect Rates | Mean Rate | 2 Sigma Limit | 3 Sigma Limit | |
|---|---|---|---|---|---|---|---|---|
| 0 | Product A | 201607.0 | 37.0 | 222.000000 | 166666.666667 | 81319.08913 | 188681.909296 | 242363.319379 |
| 1 | Product A | 201608.0 | 26.0 | 36.000000 | 722222.222222 | 81319.08913 | 188681.909296 | 242363.319379 |
| 2 | Product A | 201609.0 | 66.0 | 375.000000 | 176000.000000 | 81319.08913 | 188681.909296 | 242363.319379 |
| 3 | Product A | 201610.0 | 61.0 | 494.000000 | 123481.781377 | 81319.08913 | 188681.909296 | 242363.319379 |
| 4 | Product A | 201611.0 | 64.0 | 980.333333 | 65283.917035 | 81319.08913 | 188681.909296 | 242363.319379 |
In [3]:
print(df_a.shape)
df_a.info()
(111, 8) <class 'pandas.core.frame.DataFrame'> RangeIndex: 111 entries, 0 to 110 Data columns (total 8 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Product 28 non-null object 1 Month ID (YYYYMM) 24 non-null float64 2 Defects 24 non-null float64 3 Opportunities 24 non-null float64 4 Defect Rates 24 non-null float64 5 Mean Rate 24 non-null float64 6 2 Sigma Limit 24 non-null float64 7 3 Sigma Limit 24 non-null float64 dtypes: float64(7), object(1) memory usage: 7.1+ KB
In [4]:
df_a.head(30) # Display first 30 rows of the data
Out[4]:
| Product | Month ID (YYYYMM) | Defects | Opportunities | Defect Rates | Mean Rate | 2 Sigma Limit | 3 Sigma Limit | |
|---|---|---|---|---|---|---|---|---|
| 0 | Product A | 201607.0 | 37.0 | 222.000000 | 166666.666667 | 81319.08913 | 188681.909296 | 242363.319379 |
| 1 | Product A | 201608.0 | 26.0 | 36.000000 | 722222.222222 | 81319.08913 | 188681.909296 | 242363.319379 |
| 2 | Product A | 201609.0 | 66.0 | 375.000000 | 176000.000000 | 81319.08913 | 188681.909296 | 242363.319379 |
| 3 | Product A | 201610.0 | 61.0 | 494.000000 | 123481.781377 | 81319.08913 | 188681.909296 | 242363.319379 |
| 4 | Product A | 201611.0 | 64.0 | 980.333333 | 65283.917035 | 81319.08913 | 188681.909296 | 242363.319379 |
| 5 | Product A | 201612.0 | 104.0 | 1297.666667 | 80143.847932 | 81319.08913 | 188681.909296 | 242363.319379 |
| 6 | Product A | 201701.0 | 86.0 | 2292.000000 | 37521.815009 | 81319.08913 | 188681.909296 | 242363.319379 |
| 7 | Product A | 201702.0 | 98.0 | 2444.666667 | 40087.264794 | 81319.08913 | 188681.909296 | 242363.319379 |
| 8 | Product A | 201703.0 | 130.0 | 2460.333333 | 52838.368785 | 81319.08913 | 188681.909296 | 242363.319379 |
| 9 | Product A | 201704.0 | 107.0 | 1888.666667 | 56653.723968 | 81319.08913 | 188681.909296 | 242363.319379 |
| 10 | Product A | 201705.0 | 135.0 | 1939.666667 | 69599.587558 | 81319.08913 | 188681.909296 | 242363.319379 |
| 11 | Product A | 201706.0 | 158.0 | 2173.000000 | 72710.538426 | 81319.08913 | 188681.909296 | 242363.319379 |
| 12 | Product A | 201707.0 | 116.0 | 2268.000000 | 51146.384480 | 81319.08913 | 188681.909296 | 242363.319379 |
| 13 | Product A | 201708.0 | 226.0 | 2188.000000 | 103290.676417 | 81319.08913 | 188681.909296 | 242363.319379 |
| 14 | Product A | 201709.0 | 171.0 | 2299.333333 | 74369.382430 | 81319.08913 | 188681.909296 | 242363.319379 |
| 15 | Product A | 201710.0 | 124.0 | 2199.000000 | 56389.267849 | 81319.08913 | 188681.909296 | 242363.319379 |
| 16 | Product A | 201711.0 | 119.0 | 2543.000000 | 46795.123869 | 81319.08913 | 188681.909296 | 242363.319379 |
| 17 | Product A | 201712.0 | 146.0 | 2779.666667 | 52524.283487 | 81319.08913 | 188681.909296 | 242363.319379 |
| 18 | Product A | 201801.0 | 134.0 | 2133.000000 | 62822.315987 | 81319.08913 | 188681.909296 | 242363.319379 |
| 19 | Product A | 201802.0 | 152.0 | 2167.333333 | 70132.266995 | 81319.08913 | 188681.909296 | 242363.319379 |
| 20 | Product A | 201803.0 | 170.0 | 2143.666667 | 79303.374281 | 81319.08913 | 188681.909296 | 242363.319379 |
| 21 | Product A | 201804.0 | 126.0 | 2841.333333 | 44345.377757 | 81319.08913 | 188681.909296 | 242363.319379 |
| 22 | Product A | 201805.0 | 134.0 | 3515.666667 | 38115.103821 | 81319.08913 | 188681.909296 | 242363.319379 |
| 23 | Product A | 201806.0 | 243.0 | 3214.666667 | 75591.041062 | 81319.08913 | 188681.909296 | 242363.319379 |
| 24 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 25 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 26 | Chart 1 | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 27 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 28 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 29 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
In [5]:
df_a = df_a.iloc[:24] # Drop the rows with missing values
In [6]:
df_a.nunique() # Check for unique values
Out[6]:
Product 1 Month ID (YYYYMM) 24 Defects 23 Opportunities 24 Defect Rates 24 Mean Rate 1 2 Sigma Limit 1 3 Sigma Limit 1 dtype: int64
In [7]:
print(df_a.isnull().sum()) # There's no missing values
Product 0 Month ID (YYYYMM) 0 Defects 0 Opportunities 0 Defect Rates 0 Mean Rate 0 2 Sigma Limit 0 3 Sigma Limit 0 dtype: int64
In [8]:
df_a.head()
Out[8]:
| Product | Month ID (YYYYMM) | Defects | Opportunities | Defect Rates | Mean Rate | 2 Sigma Limit | 3 Sigma Limit | |
|---|---|---|---|---|---|---|---|---|
| 0 | Product A | 201607.0 | 37.0 | 222.000000 | 166666.666667 | 81319.08913 | 188681.909296 | 242363.319379 |
| 1 | Product A | 201608.0 | 26.0 | 36.000000 | 722222.222222 | 81319.08913 | 188681.909296 | 242363.319379 |
| 2 | Product A | 201609.0 | 66.0 | 375.000000 | 176000.000000 | 81319.08913 | 188681.909296 | 242363.319379 |
| 3 | Product A | 201610.0 | 61.0 | 494.000000 | 123481.781377 | 81319.08913 | 188681.909296 | 242363.319379 |
| 4 | Product A | 201611.0 | 64.0 | 980.333333 | 65283.917035 | 81319.08913 | 188681.909296 | 242363.319379 |
In [9]:
df_a['Month ID (YYYYMM)'] = df_a['Month ID (YYYYMM)'].astype(int).astype(str) # Convert the Month ID to string
df_a['Date'] = pd.to_datetime(df_a['Month ID (YYYYMM)'], format='%Y%m') # Convert the Month ID to datetime
In [10]:
df_a.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 24 entries, 0 to 23 Data columns (total 9 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Product 24 non-null object 1 Month ID (YYYYMM) 24 non-null object 2 Defects 24 non-null float64 3 Opportunities 24 non-null float64 4 Defect Rates 24 non-null float64 5 Mean Rate 24 non-null float64 6 2 Sigma Limit 24 non-null float64 7 3 Sigma Limit 24 non-null float64 8 Date 24 non-null datetime64[ns] dtypes: datetime64[ns](1), float64(6), object(2) memory usage: 1.8+ KB
1. Create Chart #1 below the data set that shows the number of Defects over time.¶
In [11]:
py_offline.init_notebook_mode(connected=True) # for offline plot
fig = px.scatter(df_a, x="Date", y="Defects", title="Defects (historical)")
fig.update_traces(marker=dict(size=10))
fig.add_traces(px.line(df_a, x="Date", y="Defects").data)
fig.update_traces(line=dict(width=4), selector=dict(type='scatter', mode='lines'))
fig.update_layout(title=dict(x=0.5, font=dict(size=24)))
py_offline.iplot(fig)
2. Create Chart #2 below the data set that shows the number of Opportunities over time.¶
In [12]:
fig = px.scatter(df_a, x="Date", y="Opportunities", title="Opportunities (historical)")
fig.update_traces(marker=dict(size=10))
fig.add_traces(px.line(df_a, x="Date", y="Opportunities").data)
fig.update_traces(line=dict(width=4), selector=dict(type='scatter', mode='lines'))
fig.update_layout(title=dict(x=0.5, font=dict(size=24)))
py_offline.iplot(fig)# fig.show()
3. Create Chart #3 below the data set that shows the Defect Rates with the Mean Rate and Limits over time.¶
In [13]:
fig = go.Figure()
# 2 Sigma Limit
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['2 Sigma Limit'],
mode='none',
name='2 Sigma Limit',
fill = 'tozeroy'))
# 3 Sigma Limit
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['3 Sigma Limit'],
mode='none',
name='3 Sigma Limit',
fill='tozeroy'))
# Defect Rates
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['Defect Rates'],
mode='lines+markers',
name='Defect Rates',
line=dict(width=3),
marker=dict(size=10)
))
# Mean Rate
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['Mean Rate'],
mode='lines',
name='Mean Rate',
line=dict(color='red', width=3)))
# Update layout
fig.update_layout(title='Defect Rates [Defects/Opportunities] (historical)',
xaxis_title='Date',
yaxis_title='Rate',
title_x=0.5,
title_font=dict(size=22))
fig.update_layout(title=dict(x=0.5, font=dict(size=24)))
py_offline.iplot(fig)
4. Create Chart #4 below the data set that shows all the information from Chart #1, Chart #2, and Chart #3. Chart #4 must be presentable to key stakeholders with different levels of mastery on the data (ranging from individual contributors to senior management and executives). Be mindful of formatting, clarify, and aesthetics.¶
In [14]:
# Create plot with 2 rows and 1 column
fig = make_subplots(rows=2, cols=1, subplot_titles=("Defects & Opportunities (historical)", "Defect Rates (historical)"))
# Graph A: Defects
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['Defects'], mode='lines+markers', name='Defects', line=dict(width=4, color='#EF553B'), marker=dict(size=10), legendgroup='Group1'),
row=1, col=1)
# Graph B: Opportunities
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['Opportunities'], mode='lines+markers', name='Opportunities', line=dict(width=4, color='#00CC96'), marker=dict(size=10), legendgroup='Group2'),
row=1, col=1)
# Graph C: Defect Rates, Mean Rate, and Sigma Limits
# 2 Sigma Limit
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['2 Sigma Limit'], mode='none', name='2 Sigma (95%)', fill='tonexty', fillcolor='rgba(255, 253, 150, 0.3)', legendgroup='Group5'),
row=2, col=1)
# 3 Sigma Limit
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['3 Sigma Limit'], mode='none', name='3 Sigma (99%)', fill='tonexty', fillcolor='rgba(255, 155, 0, 0.3)', legendgroup='Group6'),
row=2, col=1)
# Defect Rates
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['Defect Rates'], mode='lines+markers', name='Defect Rates', line=dict(width=4, color = '#636EFA'), marker=dict(size=10), legendgroup='Group3'),
row=2, col=1)
# Mean Rate
fig.add_trace(go.Scatter(x=df_a['Date'], y=df_a['Mean Rate'], mode='lines', name='Mean Rate', line=dict(color='red', width=4, dash='dash'), legendgroup='Group4'),
row=2, col=1)
# Update layout
fig.update_layout(height=800, showlegend=True, legend=dict(y=0.5))
fig.update_yaxes(title_text="Units", row=1, col=1)
fig.update_yaxes(title_text="Rate units", row=2, col=1)
py_offline.iplot(fig)
5. Analyze Chart #4 and annotate at least three observations / findings specific to the data provided.¶
- Both Defects and Opportunities have increased in time.
- There are more Opportunities than Defects in all times. Nevertheless, July, August and September 2016, the difference between them is lower.
- Defect Rates is defined as Defects/Opportunities (multiplied by 10^6). If Defects trace is divided by the Opportunities trace then the Defect Rates trace is obtained.
- It seems that the Defect Rate from August 2016 could be a potential outlier, indicating a possible anomaly in the process.
- August 2016 Defect Rate value is real high due to Defects and Opportunities are very close. It seems that the higher Opportunities compared to Defects, the lower the Defect Rate is, and viceversa.
- Besides August 2016 Defect Rate value, all of the historical values fall within 2 Sigma, i.e. are inside the 95% of the values.
- We are using parametrical statistics (Mean, and Sigmas) to analyze a non-normal distribution of Defect Rates (check the Addendum - Normality test at the end of this notebook), it would be recommended to use the non-parametrical statistics (Median and Interquartil range). If we had access to the original data, we could use boxplots instead.
Task B¶
Read & Explore Data¶
In [15]:
df_b = pd.read_excel('Take Home Technical Screen.xlsx', sheet_name='Task B') # read Task B data
df_b.head()
Out[15]:
| Complaint.Number | Date | Product | Quantity | Defect | Account.Number | |
|---|---|---|---|---|---|---|
| 0 | CN-000132 | 2020-01-01 | Prod-05 | 9 | HW-ERROR-61 | Account-407 |
| 1 | CN-000133 | 2020-01-01 | Prod-00 | 6 | HW-ERROR-75 | Account-433 |
| 2 | CN-000134 | 2020-01-01 | Prod-03 | 11 | HW-ERROR-67 | Account-412 |
| 3 | CN-000135 | 2020-01-01 | Prod-09 | 4 | HW-ERROR-74 | Account-459 |
| 4 | CN-000136 | 2020-01-01 | Prod-04 | 6 | CS-ERROR-52 | Account-416 |
In [16]:
print(df_b.shape)
df_b.info()
(679, 6) <class 'pandas.core.frame.DataFrame'> RangeIndex: 679 entries, 0 to 678 Data columns (total 6 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Complaint.Number 679 non-null object 1 Date 679 non-null datetime64[ns] 2 Product 679 non-null object 3 Quantity 679 non-null int64 4 Defect 679 non-null object 5 Account.Number 679 non-null object dtypes: datetime64[ns](1), int64(1), object(4) memory usage: 32.0+ KB
In [17]:
df_b.nunique() # Check for unique values
Out[17]:
Complaint.Number 679 Date 387 Product 11 Quantity 11 Defect 51 Account.Number 76 dtype: int64
In [18]:
print(df_b.isnull().sum()) # There's no missing values
Complaint.Number 0 Date 0 Product 0 Quantity 0 Defect 0 Account.Number 0 dtype: int64
In [19]:
countries = pd.read_excel('Take Home Technical Screen.xlsx', sheet_name='Task B Country List') # read country list
countries.head()
Out[19]:
| Account.Number | Country | |
|---|---|---|
| 0 | Account-407 | Taiwan |
| 1 | Account-433 | Italy |
| 2 | Account-412 | Vietnam |
| 3 | Account-459 | Italy |
| 4 | Account-416 | Canada |
In [20]:
print(countries.shape)
countries.info()
(76, 2) <class 'pandas.core.frame.DataFrame'> RangeIndex: 76 entries, 0 to 75 Data columns (total 2 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Account.Number 76 non-null object 1 Country 76 non-null object dtypes: object(2) memory usage: 1.3+ KB
In [21]:
print(countries.isnull().sum()) # There's no missing values
Account.Number 0 Country 0 dtype: int64
1. Add Country to "Task B" sheet using mapping table provided in "Task B Country List" sheet.¶
In [22]:
df_b = df_b.merge(countries, on='Account.Number', how='left') # Merge the data with the country list
df_b.head()
Out[22]:
| Complaint.Number | Date | Product | Quantity | Defect | Account.Number | Country | |
|---|---|---|---|---|---|---|---|
| 0 | CN-000132 | 2020-01-01 | Prod-05 | 9 | HW-ERROR-61 | Account-407 | Taiwan |
| 1 | CN-000133 | 2020-01-01 | Prod-00 | 6 | HW-ERROR-75 | Account-433 | Italy |
| 2 | CN-000134 | 2020-01-01 | Prod-03 | 11 | HW-ERROR-67 | Account-412 | Vietnam |
| 3 | CN-000135 | 2020-01-01 | Prod-09 | 4 | HW-ERROR-74 | Account-459 | Italy |
| 4 | CN-000136 | 2020-01-01 | Prod-04 | 6 | CS-ERROR-52 | Account-416 | Canada |
2. Summarize "Task B" sheet reported volumes for each product; calculate percent difference between product volumes in 2020 and 2021.¶
In [23]:
df_b['Year'] = df_b['Date'].dt.year # Extract the year from the date
In [24]:
df_b.head()
Out[24]:
| Complaint.Number | Date | Product | Quantity | Defect | Account.Number | Country | Year | |
|---|---|---|---|---|---|---|---|---|
| 0 | CN-000132 | 2020-01-01 | Prod-05 | 9 | HW-ERROR-61 | Account-407 | Taiwan | 2020 |
| 1 | CN-000133 | 2020-01-01 | Prod-00 | 6 | HW-ERROR-75 | Account-433 | Italy | 2020 |
| 2 | CN-000134 | 2020-01-01 | Prod-03 | 11 | HW-ERROR-67 | Account-412 | Vietnam | 2020 |
| 3 | CN-000135 | 2020-01-01 | Prod-09 | 4 | HW-ERROR-74 | Account-459 | Italy | 2020 |
| 4 | CN-000136 | 2020-01-01 | Prod-04 | 6 | CS-ERROR-52 | Account-416 | Canada | 2020 |
In [25]:
# Segment year 2020 and 2021
df_2020 = df_b[df_b['Year'] == 2020]
df_2021 = df_b[df_b['Year'] == 2021]
# Compute product volumes for 2020 and 2021
volume_2020 = df_2020.groupby('Product')['Quantity'].sum().reset_index()
volume_2021 = df_2021.groupby('Product')['Quantity'].sum().reset_index()
# Merge 2020 and 2021 product volumes
merged_data = pd.merge(volume_2020, volume_2021, on='Product', suffixes=('_2020', '_2021'))
# Compute product volume for both years
merged_data['Quantity_2020+2021'] = merged_data['Quantity_2020'] + merged_data['Quantity_2021']
# Compute the percent difference between 2021 and 2020
merged_data['Percent_Difference'] = ((merged_data['Quantity_2021'] - merged_data['Quantity_2020']) / merged_data['Quantity_2020']) * 100
In [26]:
merged_data
Out[26]:
| Product | Quantity_2020 | Quantity_2021 | Quantity_2020+2021 | Percent_Difference | |
|---|---|---|---|---|---|
| 0 | Prod-00 | 140 | 75 | 215 | -46.428571 |
| 1 | Prod-01 | 208 | 214 | 422 | 2.884615 |
| 2 | Prod-02 | 192 | 199 | 391 | 3.645833 |
| 3 | Prod-03 | 282 | 196 | 478 | -30.496454 |
| 4 | Prod-04 | 189 | 160 | 349 | -15.343915 |
| 5 | Prod-05 | 261 | 179 | 440 | -31.417625 |
| 6 | Prod-06 | 284 | 225 | 509 | -20.774648 |
| 7 | Prod-07 | 193 | 130 | 323 | -32.642487 |
| 8 | Prod-08 | 169 | 198 | 367 | 17.159763 |
| 9 | Prod-09 | 323 | 125 | 448 | -61.300310 |
| 10 | Prod-10 | 125 | 99 | 224 | -20.800000 |
In [27]:
merged_data['Legend_Labels'] = merged_data['Product'] + " (" + merged_data['Quantity_2020+2021'].astype(str) + ")"
fig = px.pie(merged_data, values='Quantity_2020+2021', names='Legend_Labels', title='Volume by Product (2020-2021)')
fig.update_layout(title=dict(x=0.5, font=dict(size=24)), width=500, height=500)
py_offline.iplot(fig)
In [28]:
fig = px.bar(merged_data, x='Product', y='Percent_Difference',
title='Percentage difference in reported volume between 2020-2021',
text='Percent_Difference', color='Product')
fig.update_traces(texttemplate='%{text:.2f}%', textposition='outside')
fig.update_layout(uniformtext_minsize=8, uniformtext_mode='hide',
yaxis=dict(title='Percentage difference (%)'),
xaxis=dict(title='Product'))
fig.update_layout(title=dict(x=0.5, font=dict(size=24))) # Center the title
fig.update_yaxes(range=[-75, 75]) # Set the y-axis range
fig.add_hline(y=0, line_dash="dash", line_color="black") # Add a horizontal line at 0
py_offline.iplot(fig)
3. Identify the top 3 countries with highest complaint volume in year 2020.¶
In [29]:
df_2020 = df_b[df_b['Year'] == 2020] # Filter the data for 2020
In [30]:
df_2020.groupby('Country').size().sort_values(ascending=False).head(3) # Mexico, Taiwan, and China are the top 3 countries with highest complaint volume in 2020
Out[30]:
Country Mexico 64 Taiwan 50 Italy 45 dtype: int64
4. Defects are tagged as either HW, SW, or CS errors. Summarize complaint volumes for each of these categories.¶
In [31]:
df_b['Defect_Category'] = df_b['Defect'].str[:2] # Extract the first two characters of the defect code
In [32]:
defect_counts = df_b['Defect_Category'].value_counts()
print(defect_counts)
Defect_Category SW 300 HW 257 CS 122 Name: count, dtype: int64
In [33]:
labels_with_counts = [f'{index} ({value})' for index, value in defect_counts.items()]
fig = px.pie(defect_counts, values='count', names=labels_with_counts, title='Defect Categories (2020-2021)')
fig.update_layout(title=dict(x=0.5, font=dict(size=24)), width=500, height=500)
py_offline.iplot(fig)
Addendum - Normality test¶
In [34]:
df_a['Defect Rates'].describe() # Mean and Median (50%) are not so close, so the data is possibly not-normally distributed
Out[34]:
count 24.000000 mean 100751.430509 std 137216.102210 min 37521.815009 25% 52179.808735 50% 67441.752297 75% 79513.492694 max 722222.222222 Name: Defect Rates, dtype: float64
In [35]:
plt.hist(df_a['Defect Rates'], bins='auto', alpha=0.7, rwidth=0.85, color='blue')
plt.title('Histogram of Defect Rates')
plt.show()
In [36]:
print(max(df_a['Defect Rates'])) # Possible outlier
722222.2222222222
In [37]:
defect_rates = df_a['Defect Rates'][df_a['Defect Rates'] != max(df_a['Defect Rates'])] # Remove the possible outlier
In [38]:
# Histogram without the outlier doesn't seems to be normally distributed
plt.hist(defect_rates, bins='auto', alpha=0.7, rwidth=0.85, color='blue')
plt.title('Histogram of Defect Rates')
plt.show()
In [39]:
# Q-Q plot without the outlier indicates that the data is not normally distributed
stats.probplot(defect_rates, dist="norm", plot=plt)
plt.title('Gráfico Q-Q')
plt.show()
In [40]:
# Shapiro-Wilk statistics indicates could be a normal distribution
# Nevertheless, the p-value is less than 0.05, so we reject the null hypothesis that the data is normally distributed, i.e. it's not normally distributed
shapiro_test = stats.shapiro(defect_rates)
print(f"Shapiro-Wilk test statistic: {shapiro_test[0]}, p-value: {shapiro_test[1]}")
Shapiro-Wilk test statistic: 0.7896416187286377, p-value: 0.0002627919602673501