extra_scripts/histograms.tex

\documentclass[tikz]{standalone}
\usepackage{pgfplots}
\usepackage{pgfplotstable}
\pgfplotsset{compat=1.17}

\begin{document}

% Load the dataset
\pgfplotstableread[col sep=comma]{data/processed/v2_merged_selected_features_with_missing.csv}\datatable

\begin{tikzpicture}

% Main title at the top
\node[align=center] at (7, 3.75) {\textbf{Distributions of Environmental Variables}};

% First row of plots
\begin{axis}[
    at={(0,0)},
    width=5.5cm,
    xlabel=PM$_{2.5}$ ($\mu g /m^3$),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ylabel=Frequency,
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=1] {\datatable};
\end{axis}

\begin{axis}[
    at={(5cm,0)},
    width=5.5cm,
    tick label style={font=\fontsize{8}{8}\selectfont},
    xlabel=PM$_{10}$ ($\mu g /m^3$),
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=2] {\datatable};
\end{axis}

\begin{axis}[
    at={(10cm,0)},
    width=5.5cm,
    tick label style={font=\fontsize{8}{8}\selectfont},
    xlabel=O$_{3}$ ($\mu g /m^3$),
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=3] {\datatable};
\end{axis}

% Second row of plots
\begin{axis}[
    at={(0,-5cm)},
    width=5.5cm,
    xlabel=NO$_{2}$ ($\mu g /m^3$),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ylabel=Frequency,
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=4] {\datatable};
\end{axis}

\begin{axis}[
    at={(5cm,-5cm)},
    width=5.5cm,
    xlabel=Temperature (°C),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=5] {\datatable};
\end{axis}

\begin{axis}[
    at={(10cm,-5cm)},
    width=5.5cm,
    xlabel=Humidity (\%),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=6] {\datatable};
\end{axis}

% Third row of plots
\begin{axis}[
    at={(0,-10cm)},
    width=5.5cm,
    xlabel=Visibility ($km$),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ylabel=Frequency,
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=7] {\datatable};
\end{axis}

\begin{axis}[
    at={(5cm,-10cm)},
    width=5.5cm,
    xlabel=Solar Radiation ($W/m^2$),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=8] {\datatable};
\end{axis}

\begin{axis}[
    at={(10cm,-10cm)},
    width=5.5cm,
    xlabel=Precipitation ($mm$),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=9] {\datatable};
\end{axis}

\begin{axis}[
    at={(2cm,-15cm)},
    width=5.5cm,
    xlabel=Windspeed ($km/h$),
    ylabel=Frequency,
    tick label style={font=\fontsize{8}{8}\selectfont},
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=10] {\datatable};
\end{axis}

\begin{axis}[
    at={(8cm,-15cm)},
    width=5.5cm,
    xlabel=Wind Direction (degrees),
    tick label style={font=\fontsize{8}{8}\selectfont},
    ybar=0pt, bar width=1,
]
\addplot+[fill=cyan,
    fill opacity=0.5,
    hist={bins=20}
] table [y index=11] {\datatable};
\end{axis}

\end{tikzpicture}
\end{document}