Jose RF Junior JoseRFJuniorLLMs

## Data.csv

          
            País
             Idade
             Salário
             Comprado

            
              France
              44
              72000
              No

            
              Spain
              27
              48000
              Yes

            
              Germany
              30
              54000
              No

            
              Spain
              38
              61000
              No

            
              Germany
              40
              
              Yes

            
              France
              35
              58000
              Yes

            
              Spain
              
              52000
              No

            
              France
              48
              79000
              Yes

            
              Germany
              50
              83000
              No

## categorical_data.R
# Data Preprocessing

# Importing the dataset
dataset = read.csv('Data.csv')

# Taking care of missing data
dataset$Age = ifelse(is.na(dataset$Age),
                     ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)),
                     dataset$Age)
dataset$Salary = ifelse(is.na(dataset$Salary),

## missing_data.py
# Data Preprocessing

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Data.csv')
X = dataset.iloc[:, :-1].values

## missing_data.R
# Data Preprocessing

# Importing the dataset
dataset = read.csv('Data.csv')

# Taking care of missing data
dataset$Age = ifelse(is.na(dataset$Age),
                     ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)),
                     dataset$Age)
dataset$Salary = ifelse(is.na(dataset$Salary),

## knn.py
# K-Nearest Neighbors (K-NN)

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values

## knn.R
# K-Nearest Neighbors (K-NN)

# Importing the dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]

# Encoding the target feature as factor
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set

## Social_Network_Ads.csv

          
            IDdousuário
             gênero
             idade
             salárioestimado
             comprado

            
              15624510
              Male
              19
              19000
              0

            
              15810944
              Male
              35
              20000
              0

            
              15668575
              Female
              26
              43000
              0

            
              15603246
              Female
              27
              57000
              0

            
              15804002
              Male
              19
              76000
              0

            
              15728773
              Male
              27
              58000
              0

            
              15598044
              Female
              27
              84000
              0

            
              15694829
              Female
              32
              150000
              1

            
              15600575
              Male
              25
              33000
              0

## classification_template.py
# Classification template

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values

## classification_template.R
# Classification template

# Importing the dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]

# Encoding the target feature as factor
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set

## knn.py
# K-Nearest Neighbors (K-NN)

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
País	Idade	Salário	Comprado
France	44	72000	No
Spain	27	48000	Yes
Germany	30	54000	No
Spain	38	61000	No
Germany	40		Yes
France	35	58000	Yes
Spain		52000	No
France	48	79000	Yes
Germany	50	83000	No
	# Data Preprocessing

	# Importing the dataset
	dataset = read.csv('Data.csv')

	# Taking care of missing data
	dataset$Age = ifelse(is.na(dataset$Age),
	ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)),
	dataset$Age)
	dataset$Salary = ifelse(is.na(dataset$Salary),
	# Data Preprocessing

	# Importing the libraries
	import numpy as np
	import matplotlib.pyplot as plt
	import pandas as pd

	# Importing the dataset
	dataset = pd.read_csv('Data.csv')
	X = dataset.iloc[:, :-1].values
	# K-Nearest Neighbors (K-NN)

	# Importing the libraries
	import numpy as np
	import matplotlib.pyplot as plt
	import pandas as pd

	# Importing the dataset
	dataset = pd.read_csv('Social_Network_Ads.csv')
	X = dataset.iloc[:, [2, 3]].values
	# K-Nearest Neighbors (K-NN)

	# Importing the dataset
	dataset = read.csv('Social_Network_Ads.csv')
	dataset = dataset[3:5]

	# Encoding the target feature as factor
	dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

	# Splitting the dataset into the Training set and Test set
IDdousuário	gênero	idade	salárioestimado	comprado
15624510	Male	19	19000	0
15810944	Male	35	20000	0
15668575	Female	26	43000	0
15603246	Female	27	57000	0
15804002	Male	19	76000	0
15728773	Male	27	58000	0
15598044	Female	27	84000	0
15694829	Female	32	150000	1
15600575	Male	25	33000	0
	# Classification template

	# Importing the libraries
	import numpy as np
	import matplotlib.pyplot as plt
	import pandas as pd

	# Importing the dataset
	dataset = pd.read_csv('Social_Network_Ads.csv')
	X = dataset.iloc[:, [2, 3]].values