CS109A Introduction to Data Science

# set the colors
cmap = plt.get_cmap('Pastel1')
young = cmap(0.5)
middle = cmap(0.2)
older = cmap(0.8)

# get the object we will change - patches is an array with len: num of bins
fig, ax = plt.subplots()
y_values, bins, patches = ax.hist(titanic.age, 10)

[patches[i].set_facecolor(young) for i in range(0,1)] # bin 0
[patches[i].set_facecolor(middle) for i in range(1,3)] # bins 1 and 2
[patches[i].set_facecolor(older) for i in range(3,10)] # 7 remaining bins 

ax.grid(True)
fig.show()

sns.kdeplot(titanic.age, bw=0.6, label="bw: 0.6", shade=True, color="r");
sns.kdeplot(titanic.age, bw=2, label="bw: 2", shade=True);

# your code here
sns.kdeplot(titanic.fare, bw=0.5, label="bw: 0.5", shade=True);

import seaborn as sns
sns.set(color_codes=True)

x1 = np.random.normal(size=100)
x2 = np.random.normal(size=100)

fig, ax = plt.subplots(1,2, figsize=(15,5))

# seaborn goes in first subplot
sns.set(font_scale=0.5)
sns.distplot(x1, kde=False, bins=15, ax=ax[0]);
sns.distplot(x2, kde=False, bins=15, ax=ax[0]);
ax[0].set_title('seaborn Graph Here', fontsize=14)
ax[0].set_xlabel(r'$x$', fontsize=14)
ax[0].set_ylabel(r'$count$', fontsize=14)

# matplotlib goes in second subplot
ax[1].hist(x1, alpha=0.2, bins=15, label=r'$x1$');
ax[1].hist(x2, alpha=0.5, bins=15, label=r'$x2$');
ax[1].set_xlabel(r'$x$', fontsize=14)
ax[1].set_ylabel(r'$count$', fontsize=14)
ax[1].set_title('matplotlib Graph Here', fontsize=14)
ax[1].legend(loc='best', fontsize=14);

columns = ["age", "sex", "cp", "restbp", "chol", "fbs", "restecg", 
           "thalach", "exang", "oldpeak", "slope", "ca", "thal", "num"]
heart_df = pd.read_csv('../data/heart_disease.csv', header=None, names=columns)

heart_df.head()

# seaborn
ax = sns.boxplot(x='age', data=titanic)
#ax = sns.boxplot(x=titanic['age']) # another way to write this
ax.set_ylabel(None);
ax.set_xlabel('age', fontsize=14);
ax.set_title('Distribution of age in the Titanic', fontsize=14);

# your code here
# two variables seaborn
ax = sns.boxplot(x="class", y="age", data=titanic)

# two variable boxplot in pandas
titanic.boxplot('age',by='class')

f, ax = plt.subplots(1,1, figsize=(10, 5))
sns.scatterplot(x="fare", y="age", data=titanic, ax=ax); 

sns.jointplot("fare", "age", data=titanic, s=40, edgecolor="w", linewidth=1)

# matplotlib
fig, ax = plt.subplots(1,1, figsize=(10,6))
ax.scatter(heart_df['age'], heart_df['restbp'], alpha=0.8);
ax.set_xlabel(r'$Age (yrs)$', fontsize=15);
ax.set_ylabel(r'Resting Blood Pressure (mmHg)', fontsize=15);
ax.set_title('Age vs. Resting Blood Pressure', fontsize=14)
plt.show();

f, ax = plt.subplots(1,1, figsize=(10, 5))
sns.scatterplot(x="fare", y="age", hue="survived", data=titanic, ax=ax);

# your code here
f, ax = plt.subplots(1,1, figsize=(10, 5))
sns.scatterplot(x="fare", y="age", hue="survived", size="sex", data=titanic, ax=ax);

titanic.columns

to_plot = ['age', 'fare', 'survived', 'deck']

df_to_plot = titanic.loc[:,to_plot]
sns.pairplot(df_to_plot);

from pandas.plotting import scatter_matrix
scatter_matrix(df_to_plot, alpha=0.8, figsize=(10, 10), diagonal='kde');

titanic = sns.load_dataset('titanic')
f, ax = plt.subplots(figsize=(7, 3));
ax = sns.countplot(y="deck", data=titanic, color="c");
ax.set_title('Titanic');

ax = sns.countplot(x="class", data=titanic)
ax.set_title('Titanic');

fig, ax = plt.subplots(figsize=(10,6)) # Create figure object
sns.set_context("notebook", font_scale=1, rc={"lines.linewidth": 2.5})
ax = sns.countplot(x="deck", data=titanic)

sns.set(style="ticks", palette="muted")
sns.relplot(x="age", y="deck", col="class", data=titanic);

sns.set_context("notebook", font_scale=1.5, rc={"lines.linewidth": 2.5})
sns.pairplot(data=titanic, hue="deck");

df = pd.DataFrame(np.random.randn(1000, 4), columns=['A', 'B', 'C', 'D'])
df.head()

# cumulative sum adds column values as it goes
df = df.cumsum()
df.head()

plt.figure();
df.plot();
plt.legend(loc='best');

ts = pd.Series(np.random.randn(1000),
               index=pd.date_range('1/1/2000', periods=1000))
df = pd.DataFrame(np.random.randn(1000, 4), 
                  index=ts.index, columns=list('ABCD'))

df = df.cumsum()
plt.figure();
df.plot();

plt.figure();
df.iloc[0].plot(kind='bar');

df2 = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df2

df2.plot.bar();

# horizontal bar plot
df2.plot.barh(stacked=False);

df4 = pd.DataFrame({'a': np.random.randn(1000) + 1, 'b': np.random.randn(1000), 
                    'c': np.random.randn(1000) - 1}, columns=['a', 'b', 'c'])

plt.figure();
df4.plot.hist(alpha=0.5, stacked=False, bins=60);

color = {'boxes': 'DarkGreen', 'whiskers': 'DarkOrange',
         'medians': 'DarkBlue', 'caps': 'Gray'}

df = pd.DataFrame(np.random.rand(10, 5), columns=['A', 'B', 'C', 'D', 'E'])
df.plot.box(color=color );

df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df.plot.area(stacked=True);

df.plot.area(stacked=False);

ax = df.plot.scatter(x='a', y='b', color='DarkBlue', label='Group 1');
df.plot.scatter(x='c', y='d', color='DarkGreen', label='Group 2', ax=ax);

# load the dataset
heart_df = pd.read_csv('../data/heart_disease.csv', header=None, names=columns)
heart_df.head()

# Replace response variable values with a binary response (1: heart disease(hd) or 0: not)
heart_df['num'].replace(to_replace=[1,2,3,4],value=1,inplace=True)

# Rename column for clarity
heart_df = heart_df.rename(columns = {'num':'hd'})
heart_df.head()

# look at the features
heart_df.info();

heart_df.describe()

# your code here
# 01. what ages do people seek cardiological exams? 

# %load solutions/q01.py
fig, ax = plt.subplots(figsize=(8,6)) 
sns.set_context("notebook", font_scale=1.5, rc={"lines.linewidth": 2.5})
ax = sns.distplot(heart_df.age, kde=False) #, bins=10);
ax.set_xlim(0, 90);
ax.set_title('Ages seeking cardio exams');
#ax.set_xlabel('age of patient')

# your code here
# 02. do men seek help more than women?

# %load solutions/q02.py
heart_df.replace({'sex': {0.: 'F', 1.: 'M'}}, inplace=True)  
# We would use a countplot
ax = sns.countplot(x="sex", data=heart_df)
ax.set_title('Count of M vs. F who seek cardio examinations');

heart_df.replace({'sex': {'F': 0., 'M': 1.}}, inplace=True)

# your code here
# 03. Examine the variables. How do they relate to one another?

# %load solutions/q03.py
categorical = ["sex", "cp", "fbs", "restecg", "exang",  "slope", "ca", "thal", "hd"]
numerical = ["age","restbp", "chol", "thalach",  "oldpeak"]

# pandas trick: give me all rows of numerical columns
sns.set_context("notebook", font_scale=1, rc={"lines.linewidth": 2.5})
df_to_plot = heart_df.loc[:,numerical]
sns.pairplot(df_to_plot);

plt.show()

# Look at correlation coefficients too
corr_matrix = heart_df.corr()
corr_matrix['hd'].sort_values(ascending=False)

# your code here
# 04. What percentage of men and women seek cardio exams? 

# %load solutions/q04.py
# first find percentages
per_men = (heart_df.sex.value_counts()[1])/(heart_df.sex.value_counts()[0]+heart_df.sex.value_counts()[1])
per_wom = (heart_df.sex.value_counts()[0])/(heart_df.sex.value_counts()[0]+heart_df.sex.value_counts()[1])
per_men, per_wom

labels = 'Men', 'Women'
explode = (0, 0.1)  # only "explode" the 2nd slice 
sizes = [per_men, per_wom]

# First and last time I will use a pie chart, let alone an exploding one!!
fig1, ax1 = plt.subplots()
ax1.pie(sizes, explode=explode, labels=labels, autopct='%1.1f%%', shadow=True, startangle=90)
ax1.axis('equal')  # Equal aspect ratio ensures that pie is drawn as a circle.
plt.show()

# your code here
# 05. Does resting blood pressure increase with age?

# %load solutions/q05.py
fig, ax = plt.subplots(figsize=(20,6)) 
ax = sns.boxplot(x="age", y="restbp", data=heart_df)
ax.set_ylabel(None);
ax.set_xlabel('age', fontsize=14);
ax.set_ylabel('restbp (mmHg)', fontsize=14);
ax.set_title('Percentile Distibution for age and rest blood pressure', fontsize=14);

mystery = pd.read_csv('../data/mystery.csv',  sep=' ', header=None) 
mystery.head()

# your code here

# this solution will be revealed in the next lab
# %load solutions/mystery.py