Random+Forest+Classifier+with+features.py

# coding: utf-8

# We import useful libraries that we are gonna use in our code

import matplotlib.pyplot as plt
get_ipython().magic('matplotlib inline')
import numpy as np
import pandas as pd
import statsmodels.api as sm
from statsmodels.nonparametric.kde import KDEUnivariate
from statsmodels.nonparametric import smoothers_lowess
from pandas import Series, DataFrame
from patsy import dmatrices
from sklearn import datasets, svm

# Import the train.csv data from the Kaggle competition

df = pd.read_csv("C:/Users/Kostas/Desktop/MSc Cloud Computing/3rd Block - Weeks 13-16/Machine Learning/OK solution/train.csv") 

df 

df = df.drop(['Ticket','Cabin'], axis=1)
# Remove NaN values
df = df.dropna() 

# specifies the parameters of our graphs
fig = plt.figure(figsize=(18,6), dpi=1600) 
alpha=alpha_scatterplot = 0.2 
alpha_bar_chart = 0.55

ax1 = plt.subplot2grid((2,3),(0,0))
# plots a bar graph of those who surived vs those who did not.               
df.Survived.value_counts().plot(kind='bar', alpha=alpha_bar_chart)
ax1.set_xlim(-1, 2)
# puts a title on our graph
plt.title("Distribution of Survival, (1 = Survived)")    

plt.subplot2grid((2,3),(0,1))
plt.scatter(df.Survived, df.Age, alpha=alpha_scatterplot)
# sets the y axis lable
plt.ylabel("Age")
# formats the grid line style of our graphs                          
plt.grid(b=True, which='major', axis='y')  
plt.title("Survival by Age,  (1 = Survived)")

ax3 = plt.subplot2grid((2,3),(0,2))
df.Pclass.value_counts().plot(kind="barh", alpha=alpha_bar_chart)
ax3.set_ylim(-1, len(df.Pclass.value_counts()))
plt.title("Class Distribution")

class_sex_grouping = df.groupby(['Pclass','Sex']).mean()
class_sex_grouping

class_sex_grouping['Survived'].plot.bar()

group_by_age = pd.cut(df["Age"], np.arange(0, 90, 10))
age_grouping = df.groupby(group_by_age).mean()
age_grouping['Survived'].plot.bar()

#Grapho of those who survived vs those who died
plt.figure(figsize=(6,4))
fig, ax = plt.subplots()
df.Survived.value_counts().plot(kind='barh', color="blue", alpha=.65)
ax.set_ylim(-1, len(df.Survived.value_counts())) 
plt.title("Survival Breakdown (1 = Survived, 0 = Died)")

fig = plt.figure(figsize=(18,6))

#create a plot of two subsets, male and female, of the survived variable.
#After we do that we call value_counts() so it can be easily plotted as a bar graph. 
#'barh' is just a horizontal bar graph
df_male = df.Survived[df.Sex == 'male'].value_counts().sort_index()
df_female = df.Survived[df.Sex == 'female'].value_counts().sort_index()

ax1 = fig.add_subplot(121)
df_male.plot(kind='barh',label='Male', alpha=0.55)
df_female.plot(kind='barh', color='#FA2379',label='Female', alpha=0.55)
plt.title("Who Survived? with respect to Gender, (raw value counts) "); plt.legend(loc='best')
ax1.set_ylim(-1, 2) 

#adjust graph to display the proportions of survival by gender
ax2 = fig.add_subplot(122)
(df_male/float(df_male.sum())).plot(kind='barh',label='Male', alpha=0.55)  
(df_female/float(df_female.sum())).plot(kind='barh', color='#FA2379',label='Female', alpha=0.55)
plt.title("Who Survived proportionally? with respect to Gender"); plt.legend(loc='best')

ax2.set_ylim(-1, 2)

fig = plt.figure(figsize=(18,4), dpi=1600)
alpha_level = 0.65

# building on the previous code, here we create an additional subset with in the gender subset 
# we created for the survived variable. I know, thats a lot of subsets. After we do that we call 
# value_counts() so it it can be easily plotted as a bar graph. this is repeated for each gender 
# class pair.
ax1=fig.add_subplot(141)
female_highclass = df.Survived[df.Sex == 'female'][df.Pclass != 3].value_counts()
female_highclass.plot(kind='bar', label='female, highclass', color='#FA2479', alpha=alpha_level)
ax1.set_xticklabels(["Survived", "Died"], rotation=0)
ax1.set_xlim(-1, len(female_highclass))
plt.title("Who Survived? with respect to Gender and Class"); plt.legend(loc='best')

ax2=fig.add_subplot(142, sharey=ax1)
female_lowclass = df.Survived[df.Sex == 'female'][df.Pclass == 3].value_counts()
female_lowclass.plot(kind='bar', label='female, low class', color='pink', alpha=alpha_level)
ax2.set_xticklabels(["Died","Survived"], rotation=0)
ax2.set_xlim(-1, len(female_lowclass))
plt.legend(loc='best')

ax3=fig.add_subplot(143, sharey=ax1)
male_lowclass = df.Survived[df.Sex == 'male'][df.Pclass == 3].value_counts()
male_lowclass.plot(kind='bar', label='male, low class',color='lightblue', alpha=alpha_level)
ax3.set_xticklabels(["Died","Survived"], rotation=0)
ax3.set_xlim(-1, len(male_lowclass))
plt.legend(loc='best')

ax4=fig.add_subplot(144, sharey=ax1)
male_highclass = df.Survived[df.Sex == 'male'][df.Pclass != 3].value_counts()
male_highclass.plot(kind='bar', label='male, highclass', alpha=alpha_level, color='steelblue')
ax4.set_xticklabels(["Died","Survived"], rotation=0)
ax4.set_xlim(-1, len(male_highclass))
plt.legend(loc='best')

# All the progress laid out together as steps
# Step 1 concerns just who lived and who died overall
# Step 2 is according to sex
# Step 3 is according to sex and class

fig = plt.figure(figsize=(18,12), dpi=1600)
a = 0.65
# Step 1
ax1 = fig.add_subplot(341)
df.Survived.value_counts().plot(kind='bar', color="blue", alpha=a)
ax1.set_xlim(-1, len(df.Survived.value_counts()))
plt.title("Step. 1")

# Step 2
ax2 = fig.add_subplot(345)
df.Survived[df.Sex == 'male'].value_counts().plot(kind='bar',label='Male')
df.Survived[df.Sex == 'female'].value_counts().plot(kind='bar', color='#FA2379',label='Female')
ax2.set_xlim(-1, 2)
plt.title("Step. 2 \nWho Survied? with respect to Gender."); plt.legend(loc='best')

ax3 = fig.add_subplot(346)
(df.Survived[df.Sex == 'male'].value_counts()/float(df.Sex[df.Sex == 'male'].size)).plot(kind='bar',label='Male')
(df.Survived[df.Sex == 'female'].value_counts()/float(df.Sex[df.Sex == 'female'].size)).plot(kind='bar', color='#FA2379',label='Female')
ax3.set_xlim(-1,2)
plt.title("Who Survied proportionally?"); plt.legend(loc='best')


# Step 3
ax4 = fig.add_subplot(349)
female_highclass = df.Survived[df.Sex == 'female'][df.Pclass != 3].value_counts()
female_highclass.plot(kind='bar', label='female highclass', color='#FA2479', alpha=a)
ax4.set_xticklabels(["Survived", "Died"], rotation=0)
ax4.set_xlim(-1, len(female_highclass))
plt.title("Who Survived? with respect to Gender and Class"); plt.legend(loc='best')

ax5 = fig.add_subplot(3,4,10, sharey=ax1)
female_lowclass = df.Survived[df.Sex == 'female'][df.Pclass == 3].value_counts()
female_lowclass.plot(kind='bar', label='female, low class', color='pink', alpha=a)
ax5.set_xticklabels(["Died","Survived"], rotation=0)
ax5.set_xlim(-1, len(female_lowclass))
plt.legend(loc='best')

ax6 = fig.add_subplot(3,4,11, sharey=ax1)
male_lowclass = df.Survived[df.Sex == 'male'][df.Pclass == 3].value_counts()
male_lowclass.plot(kind='bar', label='male, low class',color='lightblue', alpha=a)
ax6.set_xticklabels(["Died","Survived"], rotation=0)
ax6.set_xlim(-1, len(male_lowclass))
plt.legend(loc='best')

ax7 = fig.add_subplot(3,4,12, sharey=ax1)
male_highclass = df.Survived[df.Sex == 'male'][df.Pclass != 3].value_counts()
male_highclass.plot(kind='bar', label='male highclass', alpha=a, color='steelblue')
ax7.set_xticklabels(["Died","Survived"], rotation=0)
ax7.set_xlim(-1, len(male_highclass))
plt.legend(loc='best')

# Create an acceptable formula for our machine learning algorithms
formula_ml = 'Survived ~ C(Pclass) + C(Sex) + Age + SibSp + Parch + C(Embarked)'

# import the machine learning library that holds the randomforest
import sklearn.ensemble as ske

# Create the random forest model and fit the model to our training data
y, x = dmatrices(formula_ml, data=df, return_type='dataframe')
# RandomForestClassifier expects a 1 demensional NumPy array, so we convert
y = np.asarray(y).ravel()
#instantiate and fit our model
results_rf = ske.RandomForestClassifier(n_estimators=100).fit(x, y)

# Score the results
score = results_rf.score(x, y)
print ("Mean accuracy of Random Forest Predictions on the data was: {0}".format(score))

test_data = pd.read_csv("C:/Users/Kostas/Desktop/MSc Cloud Computing/3rd Block - Weeks 13-16/Machine Learning/OK solution/test.csv")

test_data

test_data['Survived'] = 1.23

results_rf = ske.RandomForestClassifier(n_estimators=100).fit(x, y)

df = pd.DataFrame(results_rf, columns=['Survived'])

results_rf = df
results_rf.to_csv("C:/Users/Kostas/Desktop/MSc Cloud Computing/3rd Block - Weeks 13-16/Machine Learning/OK solution/results.csv") # saves the results for you, change the name as you please.