import pandas as pd source_url="https://raw.githubusercontent.com/austinlasseter/hosting_some_files/main/pandas_files/Production.Product.csv"

# read the dataset as a DataFrame into a variable named 'prod_df' df = pd.read_csv(source_url, sep = '\t')

# your answer here type(df)

# your answer here print(f"The dataframe has {df.shape[0]} rows")

# your answer here print(f"The dataframe has {df.shape[1]} columns")

df.columns

# your answer here df[df.columns[15]].nunique()

# your answer here list(df[df.columns[15]].unique())

# your answer here print(f" No there are less unique values than rows. This is because some values are nan which are not counted as unqiue")

# your answer here print(df['ProductLine'].unique()[1]) len(df['ProductLine'].unique()[1])

# your answer here # there's a trailing whitespace

# your answer here df_roads = df[df['ProductLine'] == 'R '] df_roads.shape[0]

# your answer here womens_df = df[(df['ProductLine'] == 'M ') & (df['Style'] == 'W ')]

womens_df.shape[0]

# your answer here # create boolean index for women's and mountain most_expensive_df = df[((df['ProductLine'] == 'M ') & (df['Style'] == 'W ')) | (df['Color'] == 'Silver')].sort_values('ListPrice', ascending= False).nlargest(3, 'ListPrice') most_expensive_df

# create boolean index for silver silver_list = list(df['Color'] == 'Silver') silver_list[0:10]

# sort values and display most_expensive_df.set_index('ProductID', inplace = True)

final_df = pd.DataFrame(most_expensive_df[['ListPrice', 'Name']])

final_df.head()

#renaming columns final_df.rename(columns={'Name': 'NewName'}, inplace=True)

final_df