import numpy as np import pandas as pd import math import matplotlib.pyplot as plt import seaborn as sns import datetime from sklearn.neural_network import MLPClassifier from sklearn.svm import SVC from sklearn.preprocessing import StandardScaler, MinMaxScaler from sklearn.preprocessing import LabelEncoder, OneHotEncoder from sklearn.feature_extraction import DictVectorizer from sklearn.pipeline import Pipeline from sklearn.metrics import accuracy_score from sklearn import preprocessing from sklearn.model_selection import KFold from sklearn.preprocessing import normalize from sklearn.linear_model import LogisticRegression from sklearn import tree from sklearn import ensemble import warnings warnings.simplefilter('ignore')

transportation = pd.read_csv('Monthly_Transportation_Statistics (2).csv') transportation

transportation.columns

# Select relevant columns from transportation df and rename renamed = transportation.rename(columns={ 'State and Local Government Construction Spending - Water Treatment Plant': 'spending_water_treatment_plant', 'State and Local Government Construction Spending - Water Supply': 'spending_water_supply', 'State and Local Government Construction Spending - Waste Water Treatment Plant': 'spending_waste_water_treatment_plant', 'State and Local Government Construction Spending - Waste Water': 'spending_waste_water', 'State and Local Government Construction Spending - Water': 'spending_water', 'Transit Ridership - Urban Rail - Adjusted': 'ridership_urban_rail', 'Transit Ridership - Fixed Route Bus - Adjusted': 'ridership_bus_route', 'Transit Ridership - Other Transit Modes - Adjusted': 'ridership_other_transit_modes', 'Transportation Employment - Water Transportation': 'employment_water' }) transportation_clean = renamed[[ 'Date', 'spending_water_treatment_plant', 'spending_water_supply', 'spending_waste_water_treatment_plant', 'spending_waste_water', 'spending_water', 'ridership_urban_rail', 'ridership_bus_route', 'ridership_other_transit_modes', 'employment_water' ]] transportation_viz = renamed[[ 'spending_water_treatment_plant', 'spending_water_supply', 'spending_waste_water_treatment_plant', 'spending_waste_water', 'spending_water', 'employment_water' ]] transportation_clean.head()

# CATEGORICAL VISUALIZATION #1 # Transform dates into usable format, and only use data post-2018 transportation_clean['Date'] = pd.to_datetime(transportation_clean['Date']) transportation_clean['Year'] = transportation_clean.apply(lambda x: x['Date'].year, axis=1) after_2018 = transportation_clean[transportation_clean['Year'] > 2018] # Plot year vs. three different transportation types plt.figure(figsize=(12,7)) sns.lineplot(x=after_2018['Date'], y=after_2018['ridership_urban_rail'], label="Urban Rail") sns.lineplot(x=after_2018['Date'], y=after_2018['ridership_bus_route'], label="Bus Route") sns.lineplot(x=after_2018['Date'], y=after_2018['ridership_other_transit_modes'], label="Other Transit Modes") plt.title("Transit Ridership Over Time") plt.legend();

# Noticed "Other Transit Modes" didn't look like other two lines, so plotted by itself # Turns out shape was pretty much the same - only looked constant in relation to others # since they have different value ranges. plt.figure(figsize=(12,7)) sns.lineplot(x=after_2018['Date'], y=after_2018['ridership_other_transit_modes'], label="Other Transit Modes") plt.title("Other Transit Modes Ridership Over Time");

# CATEGORICAL VISUALIZATION #2 plt.figure(figsize=(12,7)) sns.barplot(x="Year", y="spending_water", data=transportation_clean[transportation_clean['Year'] > 2010]) plt.title("Distribution of Construction Spending on Water After 2010");

# QUANTITATIVE VISUALIZATION #1 # Credit: taken from Lab 7 # make a pairplot illustrating the pairwise correlations between different columns in the dataset fig = sns.pairplot(transportation_viz, plot_kws=dict(marker="o", alpha = 0.5)) for i, j in zip(*np.triu_indices_from(fig.axes, 1)): fig.axes[i, j].set_visible(False) plt.show()

transportation

# QUANTITATIVE VISUALIZATION #2 f, (ax1, ax2) = plt.subplots(1,2, figsize=(12, 7)) sns.distplot(transportation_clean['spending_water'], ax=ax1) sns.distplot(transportation_clean['employment_water'], ax=ax2) plt.show();

plt.scatter(transportation_clean['spending_water'], transportation_clean['employment_water'])