analyses_graphs.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Importing libraries\n",
    "import pandas as pd\n",
    "import re\n",
    "import bar_chart_race as bcr\n",
    "from collections import defaultdict\n",
    "import string\n",
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Opening the dataset\n",
    "ana = pd.read_csv('df_analyses.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function to clear the text of speeches\n",
    "#Taking accents out\n",
    "ana['transcription1'] = ana['transcription'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()\n",
    "\n",
    "def text_process(mess: str) -> list:\n",
    "    \"\"\"\n",
    "    Takes in a string of text, then performs the following:\n",
    "    1. Remove all stopwords\n",
    "    2. Remove all punctuation\n",
    "    3. Returns a list of the cleaned text\n",
    "    \"\"\"\n",
    "    STOPWORDS = stopwords.words('portuguese') + ['u', 'ü', '-']\n",
    "    \n",
    "    # Check characters to see if they are in punctuation\n",
    "    nopunc = [char for char in mess if char not in string.punctuation]\n",
    "\n",
    "    # Join the characters again to form the string.\n",
    "    nopunc = ''.join(nopunc)\n",
    "    \n",
    "    # Now just remove any stopwords\n",
    "    return [word for word in nopunc.split() if word.lower() not in STOPWORDS]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Running the functions\n",
    "ana['clean_transc2'] = ana.transcription1.apply(text_process)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select the relevant variables \n",
    "ana1 = ana[['deputy_code', 'keywords', 'start_time', 'full_name', 'siglaSexo', 'dataNascimento', 'party_abbreviation', 'state_abbreviation', 'clean_transc2']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Count the number of words referring to climate change\n",
    "corpus = ['CLIMA', 'ALTERACAO CLIMATICA', 'MUDANCA CLIMATICA', 'MUNDANCAS CLIMATICAS', 'AQUECIMENTO GLOBAL', \n",
    "'EFEITO ESTUFA', 'PRESERVAÇÃO', 'BIODIVERSIDADE', 'DEFESA DO MEIO AMBIENTE', 'PRESERVACAO', \n",
    "'TRANSICAO ENERGETICA', 'PROTECAO DAS FLORESTAS', 'CRISE AMBIENTAL', 'JUSTICA AMBIENTAL', 'PROTECAO DO MEIO AMBIENTE', \n",
    "'PROTECAO DA NATUREZA', 'INJUSTICA AMBIENTAL', 'CRISE CLIMÁTICA', 'POLUICAO']\n",
    "\n",
    "dic=[]\n",
    "\n",
    "for y in ana1['clean_transc2']:\n",
    "    count = 0\n",
    "    for x in corpus:\n",
    "        if x in y:\n",
    "            count+=1\n",
    "        else:\n",
    "            pass\n",
    "    dic.append(count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Adding the counting list to the df\n",
    "ana1['count'] = dic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Adjusting the dates to perform the analyzes\n",
    "ana1['data_disc'] = ana1['start_time'].str.split(pat=\"-\", expand=True)[0]\n",
    "ana1['data_nasc'] = ana1['dataNascimento'].str.split(pat=\"-\", expand=True)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select the relevant variables \n",
    "ana2 = ana1[['deputy_code', 'full_name', 'party_abbreviation', 'state_abbreviation', 'clean_transc2', 'count', 'data_disc', 'data_nasc']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Counting the cases\n",
    "count_dep = ana2.groupby(['data_disc', 'full_name']).sum('count')\n",
    "count_party = ana2.groupby(['data_disc', 'party_abbreviation']).sum('count')\n",
    "count_uf = ana2.groupby(['data_disc', 'state_abbreviation']).sum('count')\n",
    "count_data_disc = ana2.groupby(['data_disc']).sum('count')\n",
    "count_nasc = ana2.groupby(['data_disc', 'data_nasc']).sum('count')\n",
    "\n",
    "# Resetting the grouping index\n",
    "count_dep = count_dep.reset_index()\n",
    "count_party = count_party.reset_index()\n",
    "count_uf = count_uf.reset_index()\n",
    "count_data_disc = count_data_disc.reset_index()\n",
    "count_nasc = count_nasc.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Adjusting for building the animated graph\n",
    "count_dep1 = pd.pivot_table(count_dep, index=['data_disc'], columns='full_name', values='count', aggfunc='sum', fill_value=0).reset_index()\n",
    "count_party1 = pd.pivot_table(count_party, index=['data_disc'], columns='party_abbreviation', values='count', aggfunc='sum', fill_value=0).reset_index()\n",
    "count_uf1 = pd.pivot_table(count_uf, index=['data_disc'], columns='state_abbreviation', values='count', aggfunc='sum', fill_value=0).reset_index()\n",
    "count_data_disc1 = pd.pivot_table(count_data_disc, index=['data_disc'], values='count', aggfunc='sum', fill_value=0).reset_index()\n",
    "count_nasc1 = pd.pivot_table(count_nasc, index=['data_disc'], columns='data_nasc', values='count', aggfunc='sum', fill_value=0).reset_index()\n",
    "\n",
    "count_dep2 = count_dep1.set_index('data_disc')\n",
    "count_party2 = count_party1.set_index('data_disc')\n",
    "count_uf2 = count_uf1.set_index('data_disc')\n",
    "count_data_disc2 = count_data_disc1.set_index('data_disc')\n",
    "count_nasc2 = count_nasc1.set_index('data_disc')\n",
    "\n",
    "count_dep2['pad'] = 0\n",
    "count_party2['pad'] = 0\n",
    "count_uf2['pad'] = 0\n",
    "count_data_disc2['pad'] = 0\n",
    "count_nasc2['pad'] = 0\n",
    "\n",
    "count_dep2.iloc[:, 0:-1] = count_dep2.iloc[:, 0:-1].cumsum()\n",
    "count_party2.iloc[:, 0:-1] = count_party2.iloc[:, 0:-1].cumsum()\n",
    "count_uf2.iloc[:, 0:-1] = count_uf2.iloc[:, 0:-1].cumsum()\n",
    "count_data_disc2.iloc[:, 0:1] = count_data_disc2.iloc[:, 0:1].cumsum()\n",
    "count_nasc2.iloc[:, 0:-1] = count_nasc2.iloc[:, 0:-1].cumsum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Building the animated graphics\n",
    "\n",
    "# Construction of the graph by number of speeches by deputy\n",
    "bcr.bar_chart_race(df = count_dep2, \n",
    "                   n_bars = 5, \n",
    "                   sort='desc',\n",
    "                   title='Number of Speeches by Deputy',\n",
    "                   title_size='smaller',\n",
    "                   filename = 'deputado.mp4',\n",
    "                   period_length=1000,\n",
    "                   figsize=(5, 3), \n",
    "                   dpi=300, \n",
    "                   cmap='tab20',\n",
    "                   bar_label_size=5, \n",
    "                   tick_label_size=5, \n",
    "                   period_label={'family': 'Arial','x': .99, 'y': .1, 'ha': 'right', 'color': 'black'},\n",
    "                   shared_fontdict={'family': 'Arial', 'weight': 'light',\n",
    "                                    'color': 'rebeccapurple'},\n",
    "                   period_summary_func=lambda v, r: {'x': .7, 'y': .2,\n",
    "                                      's': f'Total speeches: {v.sum():,.0f}',\n",
    "                                      'ha': 'right', 'size': 8, 'family': 'Arial', 'x': .99, 'y': .05})\n",
    "\n",
    "# ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "# Construction of the graph by number of speeches by party\n",
    "bcr.bar_chart_race(df = count_party2, \n",
    "                   n_bars = 5, \n",
    "                   sort='desc',\n",
    "                   title='Number of Speeches by Party',\n",
    "                   title_size='smaller',\n",
    "                   filename = 'partido.mp4',\n",
    "                   period_length=1000,\n",
    "                   figsize=(5, 3), \n",
    "                   dpi=300, \n",
    "                   cmap='tab20',\n",
    "                   bar_label_size=5, \n",
    "                   tick_label_size=5, \n",
    "                   period_label={'family': 'Arial','x': .99, 'y': .1, 'ha': 'right', 'color': 'black'},\n",
    "                   shared_fontdict={'family': 'Arial', 'weight': 'light',\n",
    "                                    'color': 'rebeccapurple'},\n",
    "                   period_summary_func=lambda v, r: {'x': .7, 'y': .2,\n",
    "                                      's': f'Total speeches: {v.sum():,.0f}',\n",
    "                                      'ha': 'right', 'size': 8, 'family': 'Arial', 'x': .99, 'y': .05})\n",
    "\n",
    "# ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "# Construction of the graph by number of speeches by state of the deputy\n",
    "bcr.bar_chart_race(df = count_uf2, \n",
    "                   n_bars = 5, \n",
    "                   sort='desc',\n",
    "                   title=\"Number of Speeches by the Deputy's Federative Unit (UF)\",\n",
    "                   title_size='smaller',\n",
    "                   filename = 'uf.mp4',\n",
    "                   period_length=1000,\n",
    "                   figsize=(5, 3), \n",
    "                   dpi=300, \n",
    "                   cmap='tab20',\n",
    "                   bar_label_size=5, \n",
    "                   tick_label_size=5, \n",
    "                   period_label={'family': 'Arial','x': .99, 'y': .1, 'ha': 'right', 'color': 'black'},\n",
    "                   shared_fontdict={'family': 'Arial', 'weight': 'light',\n",
    "                                    'color': 'rebeccapurple'},\n",
    "                   period_summary_func=lambda v, r: {'x': .7, 'y': .2,\n",
    "                                      's': f'Total speeches: {v.sum():,.0f}',\n",
    "                                      'ha': 'right', 'size': 8, 'family': 'Arial', 'x': .99, 'y': .05})\n",
    "\n",
    "# ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "# Construction of the graph by number of speeches by date of birth of the deputy\n",
    "bcr.bar_chart_race(df = count_nasc2, \n",
    "                   n_bars = 5, \n",
    "                   sort='desc',\n",
    "                   title=\"Number of Speeches by Deputy's Date of Birth\",\n",
    "                   title_size='smaller',\n",
    "                   filename = 'nascimento.mp4',\n",
    "                   period_length=1000,\n",
    "                   figsize=(5, 3), \n",
    "                   dpi=300, \n",
    "                   cmap='tab20',\n",
    "                   bar_label_size=5, \n",
    "                   tick_label_size=5, \n",
    "                   period_label={'family': 'Arial','x': .99, 'y': .1, 'ha': 'right', 'color': 'black'},\n",
    "                   shared_fontdict={'family': 'Arial', 'weight': 'light',\n",
    "                                    'color': 'rebeccapurple'},\n",
    "                   period_summary_func=lambda v, r: {'x': .7, 'y': .2,\n",
    "                                      's': f'Total speeches: {v.sum():,.0f}',\n",
    "                                      'ha': 'right', 'size': 8, 'family': 'Arial', 'x': .99, 'y': .05})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Building the animated graphics\n",
    "#Graph - Top 5 Deputies with the highest number of speeches\n",
    "\n",
    "# Checking the 5 deputies with the most speeches during the analyzed years\n",
    "df = count_dep.groupby(['full_name']).sum().reset_index()\n",
    "df = df.sort_values('count', ascending=False)\n",
    "\n",
    "# List of desired names\n",
    "names = [\"NILTO IGNACIO TATTO\", \"MÁRCIO COSTA MACÊDO\", \"JEFFERSON ALVES DE CAMPOS\", \n",
    "         \"JOSÉ LEONARDO COSTA MONTEIRO\", \"MAGDA MOFATTO HON\"]\n",
    "\n",
    "# Select the rows where full_name is in the list of desired names\n",
    "selected_rows = df[df['full_name'].isin(names)]\n",
    "\n",
    "# Set the color palette to pastel colors\n",
    "sns.set_palette('pastel')\n",
    "\n",
    "# Create the bar plot\n",
    "ax = sns.barplot(x='count', y='full_name', data=selected_rows)\n",
    "\n",
    "# Add labels and title to the plot\n",
    "plt.xlabel('Number of Speeches')\n",
    "plt.ylabel('Deputy')\n",
    "plt.title('Top 5 Deputies with the highest number of speeches')\n",
    "\n",
    "# Add the value labels to each bar\n",
    "for i in ax.containers:\n",
    "    ax.bar_label(i,)\n",
    "\n",
    "# Save the plot to a file\n",
    "plt.savefig('top_deputies.jpeg', dpi=300, bbox_inches='tight')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n",
    "\n",
    "# -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "#Graph - Top 4 Parties with the highest number of speeches\n",
    "\n",
    "# Checking the 5 deputies with the most speeches during the analyzed years\n",
    "df = count_party.groupby(['party_abbreviation']).sum().reset_index()\n",
    "df = df.sort_values('count', ascending=False)\n",
    "\n",
    "# List of desired names\n",
    "names = ['PT', 'PL', 'PSD', 'REPUBLICANOS']\n",
    "\n",
    "# Select the rows where full_name is in the list of desired names\n",
    "selected_rows = df[df['party_abbreviation'].isin(names)]\n",
    "\n",
    "# Set the color palette to pastel colors\n",
    "sns.set_palette('pastel')\n",
    "\n",
    "# Create the bar plot\n",
    "ax = sns.barplot(x='count', y='party_abbreviation', data=selected_rows)\n",
    "\n",
    "# Add labels and title to the plot\n",
    "plt.xlabel('Number of Speeches')\n",
    "plt.ylabel('Party')\n",
    "plt.title('Top 4 Parties with the highest number of speeches')\n",
    "\n",
    "# Add the value labels to each bar\n",
    "for i in ax.containers:\n",
    "    ax.bar_label(i,)\n",
    "\n",
    "# Save the plot to a file\n",
    "plt.savefig('top_parties.jpeg', dpi=300, bbox_inches='tight')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n",
    "\n",
    "# -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "#Graph - Top 5 States that presented the highest number of speeches by their deputies\n",
    "\n",
    "# Checking the 5 deputies with the most speeches during the analyzed years\n",
    "df = count_uf.groupby(['state_abbreviation']).sum().reset_index()\n",
    "df = df.sort_values('count', ascending=False)\n",
    "\n",
    "# List of desired names\n",
    "names = ['SP', 'MG', 'RS', 'CE', 'SE']\n",
    "\n",
    "# Select the rows where full_name is in the list of desired names\n",
    "selected_rows = df[df['state_abbreviation'].isin(names)]\n",
    "\n",
    "# Set the color palette to pastel colors\n",
    "sns.set_palette('pastel')\n",
    "\n",
    "# Create the bar plot\n",
    "ax = sns.barplot(x='count', y='state_abbreviation', data=selected_rows)\n",
    "\n",
    "# Add labels and title to the plot\n",
    "plt.xlabel('Number of Speeches')\n",
    "plt.ylabel('States')\n",
    "plt.title('Top 5 states that presented the highest number of speeches by their deputies')\n",
    "\n",
    "# Add the value labels to each bar\n",
    "for i in ax.containers:\n",
    "    ax.bar_label(i,)\n",
    "\n",
    "# Save the plot to a file\n",
    "plt.savefig('top_states.jpeg', dpi=300, bbox_inches='tight')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n",
    "\n",
    "# -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "#Graph - Top 5 years with the highest number of speeches\n",
    "\n",
    "# Checking the 5 deputies with the most speeches during the analyzed years\n",
    "df = count_data_disc.groupby(['data_disc']).sum().reset_index()\n",
    "df = df.sort_values('count', ascending=False)\n",
    "\n",
    "# List of desired names\n",
    "names = ['2011', '2019', '2015', '2003', '2007']\n",
    "\n",
    "# Select the rows where full_name is in the list of desired names\n",
    "selected_rows = df[df['data_disc'].isin(names)]\n",
    "\n",
    "# Set the color palette to pastel colors\n",
    "sns.set_palette('pastel')\n",
    "\n",
    "# Create the bar plot\n",
    "ax = sns.barplot(x='count', y='data_disc', data=selected_rows)\n",
    "\n",
    "# Add labels and title to the plot\n",
    "plt.xlabel('Number of Speeches')\n",
    "plt.ylabel('Year')\n",
    "plt.title('Top 5 years with the highest number of speeches')\n",
    "\n",
    "# Add the value labels to each bar\n",
    "for i in ax.containers:\n",
    "    ax.bar_label(i,)\n",
    "\n",
    "# Save the plot to a file\n",
    "plt.savefig('top_years.jpeg', dpi=300, bbox_inches='tight')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n",
    "\n",
    "# -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n",
    "\n",
    "#Graph - Top 4 years of birth of deputies with the highest number of speeches\n",
    "\n",
    "# Checking the 5 deputies with the most speeches during the analyzed years\n",
    "df = count_nasc.groupby(['data_nasc']).sum().reset_index()\n",
    "df = df.sort_values('count', ascending=False)\n",
    "\n",
    "# List of desired names\n",
    "names = ['1963', '1971', '1970', '1962']\n",
    "\n",
    "# Select the rows where full_name is in the list of desired names\n",
    "selected_rows = df[df['data_nasc'].isin(names)]\n",
    "\n",
    "# Set the color palette to pastel colors\n",
    "sns.set_palette('pastel')\n",
    "\n",
    "# Create the bar plot\n",
    "ax = sns.barplot(x='count', y='data_nasc', data=selected_rows)\n",
    "\n",
    "# Add labels and title to the plot\n",
    "plt.xlabel('Number of Speeches')\n",
    "plt.ylabel('Year')\n",
    "plt.title('Top 4 years of birth of deputies with the highest number of speeches')\n",
    "\n",
    "# Add the value labels to each bar\n",
    "for i in ax.containers:\n",
    "    ax.bar_label(i,)\n",
    "\n",
    "# Save the plot to a file\n",
    "plt.savefig('top_nasc.jpeg', dpi=300, bbox_inches='tight')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "f8c14ae9fbdef0c4cf732716ab3acd4fcf86544210da4d9aeb48e8decd64e9fd"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}