Haydar Ali Ismail haydarai

## decision-tree-classification.py
dtc = DecisionTreeClassifier()
dtc.fit(train_inputs, train_classes)
dtc.score(test_inputs, test_classes)

## train-test-split.py
all_inputs = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']].values
all_classes = df['Species'].values

(train_inputs, test_inputs, train_classes, test_classes) = train_test_split(all_inputs, all_classes, train_size=0.7, random_state=1)

## pair-plot.py
sns.pairplot(df, hue='Species')

## plot-petal-width.py
df['PetalWidthCm'].plot.hist()
plt.show()

## df-describe.py
df.describe()

## check-dtypes.py
df.dtypes

## check-na-values.py
df.isnull().any()

## iris-imports.py
%matplotlib inline

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier

## naive-bayes-example.py
import numpy as np
from sklearn.naive_bayes import GaussianNB

X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
Y = np.array([1, 1, 1, 2, 2, 2])

clf = GaussianNB()
clf.fit(X, Y)

print(clf.predict([[-0.8, -1]]))

## dataframe.py
# Create a Spark DataFrame from Pandas
spark_df = sc.createDataFrame(pandas_df)

# Create a Pandas DataFrame from Spark
pandas_df = spark_df.toPandas()
	dtc = DecisionTreeClassifier()
	dtc.fit(train_inputs, train_classes)
	dtc.score(test_inputs, test_classes)
	all_inputs = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']].values
	all_classes = df['Species'].values

	(train_inputs, test_inputs, train_classes, test_classes) = train_test_split(all_inputs, all_classes, train_size=0.7, random_state=1)
	%matplotlib inline

	import pandas as pd
	import numpy as np
	import seaborn as sns
	import matplotlib.pyplot as plt

	from sklearn.model_selection import train_test_split
	from sklearn.tree import DecisionTreeClassifier
	import numpy as np
	from sklearn.naive_bayes import GaussianNB

	X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
	Y = np.array([1, 1, 1, 2, 2, 2])

	clf = GaussianNB()
	clf.fit(X, Y)

	print(clf.predict([[-0.8, -1]]))
	# Create a Spark DataFrame from Pandas
	spark_df = sc.createDataFrame(pandas_df)

	# Create a Pandas DataFrame from Spark
	pandas_df = spark_df.toPandas()