Functions Used

titanic_eda_functions.py

# Function to print digits on top of Barplot
def show_values(axs, orient="v", space=.01):
    def _single(ax):
        if orient == "v":
            for p in ax.patches:
                _x = p.get_x() + p.get_width() / 2
                _y = p.get_y() + p.get_height() + (p.get_height()*0.01)
                value = '{:.2f}'.format(p.get_height())
                ax.text(_x, _y, value, ha="center") 
        elif orient == "h":
            for p in ax.patches:
                _x = p.get_x() + p.get_width() + float(space)
                _y = p.get_y() + p.get_height() - (p.get_height()*0.5)
                value = '{:.2f}'.format(p.get_width())
                ax.text(_x, _y, value, ha="left")

    if isinstance(axs, np.ndarray):
        for idx, ax in np.ndenumerate(axs):
            _single(ax)
    else:
        _single(axs)

# Count Plot Function
def count_plot_function_categorical(df, feature_1, feature_2, title):
    # Set plot style
    sns.set_palette("deep")
    sns.set_style("darkgrid")
    fig, ax = plt.subplots(figsize=(24,12))
    # Plot
    sns.countplot(
        x = feature_1,
        hue = feature_2,
        data = df,
        ax = ax
    ).set_title(title)
    show_values(ax)
    
# Bar plot function
def bar_plot_function_categorical(df, feature_1, feature_2, title, feature_3 = None):
    # Set plot style
    sns.set_palette("deep")
    sns.set_style("darkgrid")
    fig, ax = plt.subplots(figsize=(24,12))
    # Plot
    sns.barplot(
        x = feature_1,
        y= feature_2,
        hue = feature_3,
        data = df,
        ci = None,
        ax = ax
    ).set_title(title)
    show_values(ax)

def dist_plot(df, feature_1, title):
    # Set plot style
    sns.set(font_scale = 1.5)
    sns.set_palette("deep")
    sns.set_style("darkgrid")
    fig, ax = plt.subplots(figsize=(18,12))
    
    f = sns.distplot(
        df[feature_1],
        bins=40, 
        ax=ax).set_title(title)

def dist_plot_survive(df, feature_1, title):
    # Set plot style
    sns.set(font_scale = 1.5)
    sns.set_palette("deep")
    sns.set_style("darkgrid")
    fig, ax = plt.subplots(figsize=(18,12))
    
    ax.set_title(title)
    g = sns.kdeplot(
        x=df["Age"],
        shade= True,
        hue=df["Survived"],
        ax=ax,
    ).set_xlabel('Age')

def swarm_plot(df, feature_1, feature_2, title):
    # Set plot style
    sns.set(font_scale = 1.5)
    sns.set_palette("deep")
    sns.set_style("darkgrid")
    fig, ax = plt.subplots(figsize=(18,12))
    
    sns.swarmplot(
        x=feature_1, 
        y=feature_2, 
        hue='Survived', 
        data=df
    ).set_title(title)