Lesson 17 Exploratory analysis

Question 1

Import the follow csv from this location, ensuring to specify that data is separated by delimiter ;

r’C:\Users\User\Documents\CFG_DATA\data\winequality-red.csv’

Answer 1

df = pd.read_csv(r’C:\Users\User\Documents\CFG_DATA\data\winequality-red.csv’, sep=’;’)

Question 2

check labels for each column

Answer 2

df.columns.values
or
df.keys()

Question 3

What is the number of rows?
Columns?

Answer 3

df.shape[0]
df.shape[1]

Question 4

Check information for each column

Answer 4

df.info()

Question 5

Return the unique values from a column called quality.

Answer 5

df.quality.unique()

Question 6

Calculate the frequency of each unique value in the “quality” column of the DataFrame df (return a Series with the unique values as the index and their respective counts as the values.)

Answer 6

df.quality.value_counts()

Question 7

Check for missing values using a heatmap

Answer 7

cbar is the colorbar

sns.heatmap(df.isnull(),cbar=False,yticklabels=False)

Question 8

calculate attributes correlation

Answer 8

df.corr()

Question 9

Build correlation heatmap

Answer 9

plt.figure(figsize=(6,4))
sns.heatmap(df.corr(),annot=False)

Question 10

Increase the size of the heatmap.

Answer 10

plt.figure(figsize=(16, 6))

Question 11

k = 12

Answer 11

specify the number of variables for the heatmap

Question 12

Question I need to figure out why it is necessary to create this new heatmap of the correlation matrix

Answer 12

Quality correlation matrix

Increase the size of the heatmap.
plt.figure(figsize=(16, 6))

k = 12 # number of variables for heatmap
cols = df.corr().nlargest(k, ‘quality’)[‘quality’].index
cm = df[cols].corr()

sns.heatmap(cm, annot=True)

Question 13

Create a boxplot

Answer 13

plt.boxplot(df_happy_gdp[‘Happiness_score’])

Set the title and labels
plt.title(‘Box Plot of Happiness Score’)
plt.xlabel(‘Happiness Score’)
plt.ylabel(‘Value’)
plt.show()