import pandas as pd import plotly.express as px import seaborn as sns

df = pd.read_csv("/content/sample_data/0083021-210914110416597.csv", sep="\t")

df

df.describe()

df.dtypes

df["eventDate"] = df["eventDate"].apply(lambda x: pd.to_datetime(x)) df["lastInterpreted"] = df["lastInterpreted"].apply(lambda x: pd.to_datetime(x))

df[df["countryCode"] == "AR"]["gbifID"].count()

df_ar = df[df["countryCode"] == "AR"]

df_ar["stateProvince"].value_counts().sort_values(ascending=False)

# Dale doble click a la derecha para ver solamente el tipo de ave que estas buscando # Github no tiene soporte para la libreria plotly, si queres ver e interactuar con el mapa podes verlo desde aca: # https://colab.research.google.com/drive/1tbHlglUFTnQj4ayVUqgFQVVqISP47KTB?usp=sharing px.set_mapbox_access_token("pk.eyJ1IjoiemVkZW1lIiwiYSI6ImNreGppeWcwNzJ1c2cydXN0NnNlbHdmZGgifQ.Go70x85Lf2IcXHez423EhA") fig = px.scatter_mapbox(df_ar, lat="decimalLatitude", lon="decimalLongitude", color="family", color_continuous_scale=px.colors.cyclical.IceFire, size_max=100, zoom=7) fig.show()

df.isnull().sum()

n = df.isnull().sum() r = [] for i in list(df_ar.columns): if n[i] == 107252: continue r.append(i) len(r) == len(list(df_ar.columns)) df_ar = df_ar[r]

df_ar

df_ar.isnull().sum()

df[df["issue"].isnull() == False]

df_ar.groupby("year")["gbifID"].count().plot.bar()

df_ar["family"].value_counts().sort_values(ascending=False)

round((df_ar["family"].value_counts().sort_values(ascending=False) / 107252) * 100, 3) # Percent

df_s_p = pd.pivot_table(df_ar, index="stateProvince")

df_s_p["count"] = df_ar[df_ar["stateProvince"] == "Buenos Aires"]["gbifID"].count() df_s_p[df_s_p.index == "La Pampa"] = df_ar[df_ar["stateProvince"] == "La Pampa"]["gbifID"].count() df_s_p[df_s_p.index == "Río Negro"] = df_ar[df_ar["stateProvince"] == "Río Negro"]["gbifID"].count()

sns.barplot(data=df_s_p, x=df_s_p.index, y="count")

df_ar["hour"] = df_ar["lastInterpreted"].apply(lambda x: x.hour)

df_ar

df_ar.groupby("hour")["gbifID"].count().plot.bar()

df_ar.groupby("day")["gbifID"].count().plot.bar()

df_ar.groupby("month")["gbifID"].count().plot.bar()

def round_station(m): if m <= 3: return "Summer" if m > 3 and m <= 6: return "Fall" if m > 6 and m <= 9: return "Winter" if m > 9 and m <= 12: return "Spring"

df_ar["roundState"] = df_ar["month"].apply(lambda x: round_station(x))

df_ar.groupby("roundState")["gbifID"].count().plot.bar()

pd.pivot_table(df_ar, index="roundState")

# Dale doble click a la derecha para ver solamente el tipo de ave que estas buscando # Github no tiene soporte para la libreria plotly, si queres ver e interactuar con el mapa podes verlo desde aca: # https://colab.research.google.com/drive/1tbHlglUFTnQj4ayVUqgFQVVqISP47KTB?usp=sharing # Sector por familia de aves px.set_mapbox_access_token("pk.eyJ1IjoiemVkZW1lIiwiYSI6ImNreGppeWcwNzJ1c2cydXN0NnNlbHdmZGgifQ.Go70x85Lf2IcXHez423EhA") df_ar["roundLatitude"] = round(df["decimalLatitude"], 1) df_ar["roundLongitude"] = round(df["decimalLongitude"], 1) fig = px.scatter_mapbox(df_ar, lat="roundLatitude", lon="roundLongitude", color="family", color_continuous_scale=px.colors.cyclical.IceFire, size_max=100, zoom=7) fig.show()