def wrangle_mall_data():
"""
This function takes acquired mall data, completes the prep
and splits the data into train, validate, and test datasets
"""
df = acquire.get_mall_data()
train, test, validate = prepare.prep_mall_data(df)
#train_and_validate, test = train_test_split(df, test_size=.15, random_state=123)
#train, validate = train_test_split(train_and_validate, test_size=.15, random_state=123)
# return train, test, validate
train_scaled, validate_scaled, test_scaled = scale_mall(train, validate, test)
return train, validate, test, train_scaled, validate_scaled, test_scaled
def wrangle_mall_clustering():
mall = acquire.get_mall_data()
mall = prepare.encode_label(mall, ['gender'])
train, validate, test = prepare.split_my_data(mall, pct=0.15)
train_scaled, validate_scaled, test_scaled = prepare.scale(train, validate, test, ['age', 'annual_income', 'gender_Male'])
return train_scaled, validate_scaled, test_scaled
import os
from acquire import get_mall_data
import scipy as sp
from sklearn.model_selection import train_test_split
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, QuantileTransformer, PowerTransformer, RobustScaler, MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from numpy import array
from numpy import argmax
# Acquire data from mall_customers.customers in mysql database.
# In[20]:
df = get_mall_data()
df.info()
# In[21]:
pd.get_dummies(df.gender, dummy_na=False, drop_first=[True, True])
# In[22]:
def clean_mall(df):
dummy_df = pd.get_dummies(df.gender,
dummy_na=False,
drop_first=[True, True])
df = pd.concat([df, dummy_df], axis=1)
# # Acquire # In[1]: import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns import env import os import acquire # In[2]: df = acquire.get_mall_data() # # Summarize # In[3]: df.shape # In[4]: df.head() # In[5]: df.dtypes