...

Full Bio

Is The Python Perfect Tool For Any Problem?

today

5 Most Popular Books Every Data Scientist Should Read That Are Not About Data Science

today

Top 10 Programming languages To Learn in 2019 - (Kotlin, Go, Python, Rust, and More)

today

An A-Z Of Useful Python Tricks - Python Developer Should Know

yesterday

Top 4 Important Reasons Data Scientists are Motivated to Change Jobs

yesterday

Which Programming Languages in Demand & Earn The Highest Salaries?

323892 views

Top 10 Best Countries for Software Engineers to Work & High in-Demand Programming Languages

273798 views

50+ Data Structure, Algorithms & Programming Languages Interview Questions for Programmers

198687 views

100+ Data Structure, Algorithms & Programming Language Interview Questions Answers for Programmers - Part 1

175665 views

Why I Studied Full-time 8 Months For A Google Programming Language Interview

147417 views

### How Hitchhiker's Guide Workes For Machine Learning in Python

**Featuring implementation code, instructional videos, and more**

- Linear Regression
- Logistic Regression
- Decision Trees
- Support Vector Machines
- K-Nearest Neighbors
- Random Forests
- K-Means Clustering
- Principal Components Analysis

import matplotlib.pyplot as plt

import numpy as np

import seaborn as sns

%matplotlib inline

from sklearn import linear_model

df = pd.read_csv(â??linear_regression_df.csvâ??)

df.columns = [â??Xâ??, â??Yâ??]

df.head()

sns.set_style(â??ticksâ??)

sns.lmplot(â??Xâ??,â??Yâ??, data=df)

plt.ylabel(â??Responseâ??)

plt.xlabel(â??Explanatoryâ??)

trainX = np.asarray(df.X[20:len(df.X)]).reshape(-1, 1)

trainY = np.asarray(df.Y[20:len(df.Y)]).reshape(-1, 1)

testX = np.asarray(df.X[:20]).reshape(-1, 1)

testY = np.asarray(df.Y[:20]).reshape(-1, 1)

linear.fit(trainX, trainY)

linear.score(trainX, trainY)

print(â??Coefficient: \nâ??, linear.coef_)

print(â??Intercept: \nâ??, linear.intercept_)

print(â??RÂ² Value: \nâ??, linear.score(trainX, trainY))

predicted = linear.predict(testX)

from sklearn.linear_model import LogisticRegression

df = pd.read_csv(â??logistic_regression_df.csvâ??)

df.columns = [â??Xâ??, â??Yâ??]

df.head()

sns.set_style(â??ticksâ??)

sns.regplot(â??Xâ??,â??Yâ??, data=df, logistic=True)

plt.ylabel(â??Probabilityâ??)

plt.xlabel(â??Explanatoryâ??)

X = (np.asarray(df.X)).reshape(-1, 1)

Y = (np.asarray(df.Y)).ravel()

logistic.fit(X, Y)

logistic.score(X, Y)

print(â??Coefficient: \nâ??, logistic.coef_)

print(â??Intercept: \nâ??, logistic.intercept_)

print(â??RÂ² Value: \nâ??, logistic.score(X, Y))

df = pd.read_csv(â??iris_df.csvâ??)

df.columns = [â??X1â??, â??X2â??, â??X3â??, â??X4â??, â??Yâ??]

df.head()

from sklearn.cross_validation import train_test_split

decision = tree.DecisionTreeClassifier(criterion=â??giniâ??)

X = df.values[:, 0:4]

Y = df.values[:, 4]

trainX, testX, trainY, testY = train_test_split( X, Y, test_size = 0.3)

decision.fit(trainX, trainY)

print(â??Accuracy: \nâ??, decision.score(testX, testY))

from IPython.display import Image

import pydotplus as pydot

dot_data = StringIO()

tree.export_graphviz(decision, out_file=dot_data)

graph = pydot.graph_from_dot_data(dot_data.getvalue())

Image(graph.create_png())

df = pd.read_csv(â??iris_df.csvâ??)

df.columns = [â??X4â??, â??X3â??, â??X1â??, â??X2â??, â??Yâ??]

df = df.drop([â??X4â??, â??X3â??], 1)

df.head()

from sklearn.cross_validation import train_test_split

support = svm.SVC()

X = df.values[:, 0:2]

Y = df.values[:, 2]

trainX, testX, trainY, testY = train_test_split( X, Y, test_size = 0.3)

support.fit(trainX, trainY)

print(â??Accuracy: \nâ??, support.score(testX, testY))

pred = support.predict(testX)

sns.set_context(â??notebookâ??, font_scale=1.1)

sns.set_style(â??ticksâ??)

sns.lmplot(â??X1â??,â??X2', scatter=True, fit_reg=False, data=df, hue=â??Yâ??)

plt.ylabel(â??X2â??)

plt.xlabel(â??X1â??)

df = pd.read_csv(â??iris_df.csvâ??)

df.columns = [â??X1â??, â??X2â??, â??X3â??, â??X4â??, â??Yâ??]

df = df.drop([â??X4â??, â??X3â??], 1)

df.head()

sns.set_style(â??ticksâ??)

sns.lmplot(â??X1â??,â??X2', scatter=True, fit_reg=False, data=df, hue=â??Yâ??)

plt.ylabel(â??X2â??)

plt.xlabel(â??X1â??)

neighbors = KNeighborsClassifier(n_neighbors=5)

X = df.values[:, 0:2]

Y = df.values[:, 2]

trainX, testX, trainY, testY = train_test_split( X, Y, test_size = 0.3)

neighbors.fit(trainX, trainY)

print(â??Accuracy: \nâ??, neighbors.score(testX, testY))

pred = neighbors.predict(testX)

df = pd.read_csv(â??iris_df.csvâ??)

df.columns = [â??X1â??, â??X2â??, â??X3â??, â??X4â??, â??Yâ??]

df.head()

forest = RandomForestClassifier()

X = df.values[:, 0:4]

Y = df.values[:, 4]

trainX, testX, trainY, testY = train_test_split( X, Y, test_size = 0.3)

forest.fit(trainX, trainY)

print(â??Accuracy: \nâ??, forest.score(testX, testY))

pred = forest.predict(testX)

df = pd.read_csv(â??iris_df.csvâ??)

df.columns = [â??X1â??, â??X2â??, â??X3â??, â??X4â??, â??Yâ??]

df = df.drop([â??X4â??, â??X3â??], 1)

df.head()

kmeans = KMeans(n_clusters=3)

X = df.values[:, 0:2]

kmeans.fit(X)

df[â??Predâ??] = kmeans.predict(X)

df.head()

sns.set_style(â??ticksâ??)

sns.lmplot(â??X1â??,â??X2', scatter=True, fit_reg=False, data=df, hue = â??Predâ??)

df = pd.read_csv(â??iris_df.csvâ??)

df.columns = [â??X1â??, â??X2â??, â??X3â??, â??X4â??, â??Yâ??]

df.head()

pca = decomposition.PCA()

fa = decomposition.FactorAnalysis()

X = df.values[:, 0:4]

Y = df.values[:, 4]

train, test = train_test_split(X,test_size = 0.3)

train_reduced = pca.fit_transform(train)

test_reduced = pca.transform(test)

pca.n_components_